TOOLS = {"search": lambda q: f"hits for {q}"} good_responses = iter([ {"stop_reason": "tool_use", "content": [{"type": "tool_use", "id": "t1", "name": "search", "input": {"q": "ramen"}}]}, {"stop_reason": "end_turn", "content": [{"type": "text", "text": "Tokyo guide."}]}, ]) bad_responses = iter([ {"stop_reason": "tool_use", "content": [{"type": "tool_use", "id": "b1", "name": "search", "input": {"q": "x"}}]}, {"stop_reason": "tool_use", "content": [{"type": "tool_use", "id": "b2", "name": "search", "input": {"q": "y"}}]}, ]) current = {"iter": good_responses} def fake_model(messages): return next(current["iter"]) def mini_harness(user_input, tools, fake_model, max_iters): messages = [{"role": "user", "content": user_input}] tool_calls_total = 0 for i in range(1, max_iters + 1): response = fake_model(messages) text_blocks = [b for b in response["content"] if b["type"] == "text"] tool_blocks = [b for b in response["content"] if b["type"] == "tool_use"] if response["stop_reason"] == "end_turn": return { "text": " ".join(b["text"] for b in text_blocks), "iters": i, "tool_calls": tool_calls_total, } tool_results = [] for block in tool_blocks: output = tools[block["name"]](**block["input"]) tool_calls_total += 1 tool_results.append({"type": "tool_result", "tool_use_id": block["id"], "content": output}) messages.append({"role": "assistant", "content": response["content"]}) messages.append({"role": "user", "content": tool_results}) return {"text": "capped", "iters": max_iters, "tool_calls": tool_calls_total} current["iter"] = good_responses r = mini_harness("find ramen", TOOLS, fake_model, 5) print(f"text={r['text']!r} iters={r['iters']} tool_calls={r['tool_calls']}") current["iter"] = bad_responses r = mini_harness("loop forever", TOOLS, fake_model, 2) print(f"text={r['text']!r} iters={r['iters']} tool_calls={r['tool_calls']}") 2e:T488,Final drill. Build a harness with all four layers measurable. Write `harness(user_input, tools, fake_model, config, max_iters)` that: - **Layer 1**: hold `system` from config in a separate `system_prompt` variable (matches Anthropic's SDK shape: `system=` is a top-level kwarg, NOT a role inside messages). Build `messages` with just the user turn. - Loop up to `max_iters`. **Layer 2**: call `fake_model(messages)` via `with_retries` (provided — retries on `TransientError`). **Layer 3**: filter content into text + tool_use blocks; track `tokens_used` from `response.get("usage", 0)`. On `end_turn`: return a result dict including layer counters. **Layer 4**: dispatch each tool_use block; track `tool_calls_total`. - Returns `{"text": str, "iters": int, "tool_calls": int, "tokens": int, "system_used": bool}`. - `system_used` is True iff the config's `system` key was held in `system_prompt` (i.e., would be sent via the SDK's top-level `system=` kwarg). Two cases run. Expected output: ``` text='Found ramen.' iters=2 tool_calls=1 tokens=130 system_used=True text='capped' iters=2 tool_calls=2 tokens=180 system_used=False ``` 2f:T613,class TransientError(Exception): transient = True def with_retries(fn, max_attempts=3): for attempt in range(max_attempts): try: return fn() except TransientError: if attempt == max_attempts - 1: raise raise RuntimeError("unreachable") TOOLS = {"search": lambda q: f"hits for {q}"} good_responses = iter([ {"stop_reason": "tool_use", "content": [{"type": "tool_use", "id": "t1", "name": "search", "input": {"q": "ramen"}}], "usage": 60}, {"stop_reason": "end_turn", "content": [{"type": "text", "text": "Found ramen."}], "usage": 70}, ]) bad_responses = iter([ {"stop_reason": "tool_use", "content": [{"type": "tool_use", "id": "b1", "name": "search", "input": {"q": "x"}}], "usage": 80}, {"stop_reason": "tool_use", "content": [{"type": "tool_use", "id": "b2", "name": "search", "input": {"q": "y"}}], "usage": 100}, ]) current = {"iter": good_responses} def fake_model(messages): return next(current["iter"]) # define harness(user_input, tools, fake_model, config, max_iters) below current["iter"] = good_responses r = harness("find ramen", TOOLS, fake_model, config={"system": "be terse"}, max_iters=5) print(f"text={r['text']!r} iters={r['iters']} tool_calls={r['tool_calls']} tokens={r['tokens']} system_used={r['system_used']}") current["iter"] = bad_responses r = harness("loop", TOOLS, fake_model, config={}, max_iters=2) print(f"text={r['text']!r} iters={r['iters']} tool_calls={r['tool_calls']} tokens={r['tokens']} system_used={r['system_used']}") 30:Tbfb,class TransientError(Exception): transient = True def with_retries(fn, max_attempts=3): for attempt in range(max_attempts): try: return fn() except TransientError: if attempt == max_attempts - 1: raise raise RuntimeError("unreachable") TOOLS = {"search": lambda q: f"hits for {q}"} good_responses = iter([ {"stop_reason": "tool_use", "content": [{"type": "tool_use", "id": "t1", "name": "search", "input": {"q": "ramen"}}], "usage": 60}, {"stop_reason": "end_turn", "content": [{"type": "text", "text": "Found ramen."}], "usage": 70}, ]) bad_responses = iter([ {"stop_reason": "tool_use", "content": [{"type": "tool_use", "id": "b1", "name": "search", "input": {"q": "x"}}], "usage": 80}, {"stop_reason": "tool_use", "content": [{"type": "tool_use", "id": "b2", "name": "search", "input": {"q": "y"}}], "usage": 100}, ]) current = {"iter": good_responses} def fake_model(messages): return next(current["iter"]) def harness(user_input, tools, fake_model, config, max_iters): # Layer 1: system_prompt is a top-level kwarg in the Anthropic # SDK, NOT a role inside messages. Keep them separate. system_prompt = config.get("system") system_used = system_prompt is not None messages = [{"role": "user", "content": user_input}] tool_calls_total = 0 tokens_used = 0 for i in range(1, max_iters + 1): response = with_retries(lambda: fake_model(messages)) tokens_used += response.get("usage", 0) text_blocks = [b for b in response["content"] if b["type"] == "text"] tool_blocks = [b for b in response["content"] if b["type"] == "tool_use"] if response["stop_reason"] == "end_turn": return { "text": " ".join(b["text"] for b in text_blocks), "iters": i, "tool_calls": tool_calls_total, "tokens": tokens_used, "system_used": system_used, } tool_results = [] for block in tool_blocks: output = tools[block["name"]](**block["input"]) tool_calls_total += 1 tool_results.append({"type": "tool_result", "tool_use_id": block["id"], "content": output}) messages.append({"role": "assistant", "content": response["content"]}) messages.append({"role": "user", "content": tool_results}) return { "text": "capped", "iters": max_iters, "tool_calls": tool_calls_total, "tokens": tokens_used, "system_used": system_used, } current["iter"] = good_responses r = harness("find ramen", TOOLS, fake_model, config={"system": "be terse"}, max_iters=5) print(f"text={r['text']!r} iters={r['iters']} tool_calls={r['tool_calls']} tokens={r['tokens']} system_used={r['system_used']}") current["iter"] = bad_responses r = harness("loop", TOOLS, fake_model, config={}, max_iters=2) print(f"text={r['text']!r} iters={r['iters']} tool_calls={r['tool_calls']} tokens={r['tokens']} system_used={r['system_used']}") 31:Tcd2,# AI-assisted is not AI-native. The difference is the question you ask. Greg Isenberg has been writing on X about small AI-native services businesses in a way that's landed harder than most "AI strategy" content. The short version: > An AI-native company is not a company that uses AI. It is a company > that has been rebuilt so AI can actually operate inside it. The > business is structured, documented, permissioned, and instrumented > in a way that agents can understand. That second sentence is the lesson. Run the editor. The two dicts show the difference as DATA, not vibes. The AI-assisted company asks "where can we add AI to save time?" The AI-native company asks "how should this workflow exist if agents are doing the first 80%?" That second question changes everything. ## The thesis: "AI cannot run on vibes" Most "AI-native" companies are, per Isenberg, "someone on the team has a ChatGPT tab open and the head of marketing made a custom GPT called Brand Voice Assistant." Cute. Useful even. Not AI-native. The real bottleneck is not the model. The model's raw outputs are strong on most well-scoped tasks. The bottleneck is that most companies are **illegible to machines** — the CRM says one thing, the Slack thread says another, the real customer history lives in someone's inbox, the pricing logic is in a spreadsheet called `Final_v7_NEW.xlsx`, the refund policy is in a Notion doc nobody trusts, the sales process is "talk to Sarah, she knows how we do enterprise." An agent walking into that company doesn't fail because of the model's outputs themselves — it fails because the surrounding scaffolding (tools, retrieval, validation, policy) has nothing to ground in: no source of truth, no rule to follow, no boundary to respect. Garbage-in, vibes-out. (We'll keep saying things like "the model decides" or "the agent figures it out" as shorthand. Recall from ch00 that this is convenience phrasing — the model is sampling the next token from a probability distribution, not deciding.) ## What this lesson is about You wrote a harness in lesson 1. The harness is the technical layer. This lesson is the ORGANIZATIONAL layer: the work you do BEFORE the harness runs to make the workflow machine-readable. We'll encode a 5-step playbook (synthesizing Isenberg's writing on AI-native services businesses) as code: 1. **Pick a narrow workflow** with high volume, existing rules, and too much human coordination. 2. **Map the workflow like a machine.** Triggers, data, decisions, reversibility, approvals, success criteria, error sites, tacit knowledge. 3. **Structure the knowledge.** Write the policy. Make pricing rules explicit. Define tone. Create examples. "It feels like documentation. It is not documentation. It is infrastructure." 4. **Put agents in with boundaries.** Let them draft, classify, recommend, enrich, summarize, prepare. Actions only where risk is understood. Approval where judgment matters. 5. **Measure business impact.** Not "hours saved." Resolution time. Conversion rate. Gross margin. Revenue per employee. By the end, you'll have `is_ai_native_ready(spec)` that takes a workflow definition and returns the same structural critique Isenberg's writing applies in prose. The framework, in code.32:Tafc,# Mapping the workflow like a machine Step 2 of the playbook is the most important and the one teams skip — the structural mapping that Isenberg's writing keeps pointing back to: > What triggers it? What data is needed? What decisions happen? > Which decisions are reversible? Which require approval? What > does success look like? Where do errors happen? What does a > human know that the system does not? Those eight questions are the workflow spec. Answer them in prose and you have a Notion doc nobody reads. Answer them in code and you have something an agent can ground its behavior in. Run the editor. The `support_triage_spec` is a triage workflow distilled into one dict. Every field a future agent would need to do the job is here. The script prints the missing fields (none), the count of decisions (four), and the ones that need approval (refund, the only irreversible action). That dict is the unit of work. Once it exists, the rest of the playbook follows mechanically. ## The four decision categories For every decision the workflow makes, two attributes determine whether the agent gets to act or needs to ask: | | Reversible | Irreversible | |-----------------|-----------|--------------| | Cheap to redo | Auto-act | Auto-act | | Expensive | Auto-act | **APPROVAL** | The only quadrant where you ALWAYS gate on a human is "irreversible + expensive." Refunding money. Sending an email to the whole list. Deleting a customer record. Closing a deal. Everything else can be drafted, recommended, classified, and shown to a human for review — but executed by the agent. ## Why this works Isenberg's general thesis: agents do the structured work, humans handle taste, trust, judgment, relationships, and exceptions. The spec is how you draw the line. Anything you wrote down is structured work. Anything you couldn't write down (the tacit_knowledge field) is the human's job. If the `tacit_knowledge` field of your spec is empty, your workflow is purely mechanical and the agent runs unsupervised. If it's a paragraph long, the agent drafts and a human reviews. If it's a page long, you're not ready to ship — start by writing the tacit knowledge down. ## What this lesson builds The next five steps walk through: - Predicting how complete a spec is (step 4) - Filling in missing required fields (step 5) - Fixing a spec that references an "implicit" policy like "ask Sarah" (step 6) - Fixing a spec whose metric is "hours saved" instead of business impact (step 7) - Writing `is_ai_native_ready(spec)` end-to-end (step 8) - Triaging three real workflow specs against the validator (step 9) By the end, you'll be able to look at a workflow at your company and grade it for AI-readiness in under a minute. The framework, in code, in your browser.33:T533,# step 2 of the playbook: map the workflow like a machine. # encode answers to eight workflow-mapping questions as a python dict. support_triage_spec = { "name": "Support ticket triage", "trigger": "ticket created in Zendesk", "inputs": ["ticket.body", "customer.history", "plan.limits", "policy.refund"], "decisions": { "classify_type": {"reversible": True, "needs_approval": False}, "draft_response": {"reversible": True, "needs_approval": False}, "issue_refund": {"reversible": False, "needs_approval": True}, "escalate_to_eng": {"reversible": False, "needs_approval": False}, }, "success_criteria": "first-response under 10min AND CSAT >= 4", "error_sites": ["wrong-account retrieval", "policy gap", "tone mismatch"], "tacit_knowledge": "when 'angry but right' looks different from 'angry and wrong'", } def required_fields(): return ["name", "trigger", "inputs", "decisions", "success_criteria", "error_sites", "tacit_knowledge"] missing = [f for f in required_fields() if f not in support_triage_spec] print(f"missing fields: {missing}") print(f"decision count: {len(support_triage_spec['decisions'])}") print(f"high-risk decisions (need approval): " f"{[d for d, r in support_triage_spec['decisions'].items() if r['needs_approval']]}") 34:T681,REQUIRED = ["name", "trigger", "inputs", "decisions", "success_criteria", "error_sites", "tacit_knowledge"] VANITY = {"hours_saved", "hours_saved_per_week", "engagement", "vibes"} good_spec = { "name": "Support triage", "trigger": "ticket.created", "inputs": ["ticket.body", "customer.history"], "decisions": {"classify": {"reversible": True, "needs_approval": False}}, "success_criteria": "first-response < 10min", "error_sites": ["wrong-account retrieval"], "tacit_knowledge": "tone with angry-but-right customers", "policies": {"refund": {"auto_approve_under": 100}}, "metrics": ["resolution_time_minutes", "csat"], } vibe_spec = { "name": "Sales outreach", "trigger": "lead.created", "inputs": ["lead.company"], "policies": {"who_to_contact": "ask Sarah, she knows"}, "metrics": ["hours_saved_per_week"], } def is_ai_native_ready(spec): present = [f for f in REQUIRED if f in spec] missing = sorted(f for f in REQUIRED if f not in spec) score = round(len(present) / len(REQUIRED), 2) policies = spec.get("policies", {}) has_explicit_policies = all(isinstance(v, dict) for v in policies.values()) if policies else True metrics = spec.get("metrics", []) business_metrics_only = not any(m in VANITY for m in metrics) ready = score >= 0.85 and has_explicit_policies and business_metrics_only return { "score": score, "missing": missing, "has_explicit_policies": has_explicit_policies, "business_metrics_only": business_metrics_only, "ready": ready, } print(is_ai_native_ready(good_spec)) print(is_ai_native_ready(vibe_spec)) 35:T965,REQUIRED = ["name", "trigger", "inputs", "decisions", "success_criteria", "error_sites", "tacit_knowledge"] VANITY = {"hours_saved", "hours_saved_per_week", "engagement", "vibes"} support_spec = { "name": "Support triage", "trigger": "ticket.created", "inputs": ["ticket.body", "customer.history"], "decisions": {"classify": {"reversible": True, "needs_approval": False}}, "success_criteria": "first-response < 10min", "error_sites": ["wrong-account retrieval"], "tacit_knowledge": "tone with angry-but-right customers", "policies": {"refund": {"auto_approve_under": 100}}, "metrics": ["resolution_time_minutes", "csat"], } sales_spec = { "name": "Sales outreach", "trigger": "lead.created", "inputs": ["lead.company", "lead.role"], "decisions": {"draft_email": {"reversible": True, "needs_approval": False}}, "success_criteria": "reply rate > 8%", "error_sites": ["bad enrichment"], "tacit_knowledge": "when to break the script", "policies": {"who_to_contact": "ask Sarah, she knows"}, # implicit "metrics": ["reply_rate", "qualified_meetings_per_week"], } onboard_spec = { "name": "Customer onboarding", "trigger": "deal.closed_won", "inputs": ["account.plan"], "decisions": {"send_welcome": {"reversible": True, "needs_approval": False}}, "policies": {"escalation": {"after_days": 3}}, "metrics": ["time_to_value_days"], # missing: success_criteria, error_sites, tacit_knowledge } def is_ai_native_ready(spec): present = [f for f in REQUIRED if f in spec] missing = sorted(f for f in REQUIRED if f not in spec) score = round(len(present) / len(REQUIRED), 2) policies = spec.get("policies", {}) has_explicit_policies = all(isinstance(v, dict) for v in policies.values()) if policies else True metrics = spec.get("metrics", []) business_metrics_only = not any(m in VANITY for m in metrics) ready = score >= 0.85 and has_explicit_policies and business_metrics_only return { "score": score, "missing": missing, "has_explicit_policies": has_explicit_policies, "business_metrics_only": business_metrics_only, "ready": ready, } # define verdict(spec) returning a string "READY" or "NOT READY: " print(f"Support: {verdict(support_spec)}") print(f"Sales: {verdict(sales_spec)}") print(f"Onboard: {verdict(onboard_spec)}") 36:Ta17,REQUIRED = ["name", "trigger", "inputs", "decisions", "success_criteria", "error_sites", "tacit_knowledge"] VANITY = {"hours_saved", "hours_saved_per_week", "engagement", "vibes"} support_spec = { "name": "Support triage", "trigger": "ticket.created", "inputs": ["ticket.body", "customer.history"], "decisions": {"classify": {"reversible": True, "needs_approval": False}}, "success_criteria": "first-response < 10min", "error_sites": ["wrong-account retrieval"], "tacit_knowledge": "tone with angry-but-right customers", "policies": {"refund": {"auto_approve_under": 100}}, "metrics": ["resolution_time_minutes", "csat"], } sales_spec = { "name": "Sales outreach", "trigger": "lead.created", "inputs": ["lead.company", "lead.role"], "decisions": {"draft_email": {"reversible": True, "needs_approval": False}}, "success_criteria": "reply rate > 8%", "error_sites": ["bad enrichment"], "tacit_knowledge": "when to break the script", "policies": {"who_to_contact": "ask Sarah, she knows"}, "metrics": ["reply_rate", "qualified_meetings_per_week"], } onboard_spec = { "name": "Customer onboarding", "trigger": "deal.closed_won", "inputs": ["account.plan"], "decisions": {"send_welcome": {"reversible": True, "needs_approval": False}}, "policies": {"escalation": {"after_days": 3}}, "metrics": ["time_to_value_days"], } def is_ai_native_ready(spec): present = [f for f in REQUIRED if f in spec] missing = sorted(f for f in REQUIRED if f not in spec) score = round(len(present) / len(REQUIRED), 2) policies = spec.get("policies", {}) has_explicit_policies = all(isinstance(v, dict) for v in policies.values()) if policies else True metrics = spec.get("metrics", []) business_metrics_only = not any(m in VANITY for m in metrics) ready = score >= 0.85 and has_explicit_policies and business_metrics_only return { "score": score, "missing": missing, "has_explicit_policies": has_explicit_policies, "business_metrics_only": business_metrics_only, "ready": ready, } def verdict(spec): r = is_ai_native_ready(spec) if r["score"] < 0.85: return f"NOT READY: incomplete spec (score={r['score']})" if not r["has_explicit_policies"]: return "NOT READY: implicit policy" if not r["business_metrics_only"]: return "NOT READY: vanity metric" return "READY" print(f"Support: {verdict(support_spec)}") print(f"Sales: {verdict(sales_spec)}") print(f"Onboard: {verdict(onboard_spec)}") 37:T11c2,# Reading other people's businesses is the cheapest education in the AI era > **Important framing before you start.** The five industries we walk > through below are **illustrative scenarios**, not actual deployments. > The Klarna anchor case at the end of this lesson is real, with > documented receipts (OpenAI case study, > Sebastian Siemiatkowski's May 2025 walk-back). The HVAC, insurance, > recruiting, support-ops, and software-dev walkthroughs are "what if > you applied this framework" explorations. They're useful for pattern > recognition. They are **not** proof the framework has shipped at any > of those specific companies. Read them as thought experiments. Read > the Klarna section as a case study. This lesson is a theory lesson. There is barely any code. That is on purpose. The previous lesson gave you a framework (`is_ai_native_ready(spec)`); this lesson gives you five examples of that framework applied to real industries. The point is pattern recognition. By the end you should be able to look at any service business and answer the question "what does this look like when 80% of the operational work is handled by agents?" If you've read the curriculum this far, you've spent most of your time on code. That's the right move when you're learning to read what AI ships you. It's the wrong move when you're trying to figure out which company to build, or which workflow at your current job to rebuild first. For that question, the bottleneck is not Python. It is **pattern intuition** — the ability to look at a messy real-world process and see the underlying machine. That intuition comes from reading case studies, not from drilling syntax. So this lesson is mostly prose. Skim it once, then come back when you're sketching a real project. ## The five industries Greg Isenberg's writing on AI-native services has named categories where AI-native companies will out-execute incumbents: agencies, brokerages, law-adjacent services, accounting firms, compliance shops, healthcare admin, real estate operations, education services, logistics coordinators, BPOs. We're going to walk through three of them in detail, then add two from elsewhere in the discourse (a process-debt-in-software-dev example, and a support-ops example). The five we'll cover: 1. **Home services** — the inbound-job-to-paid-job lifecycle 2. **Insurance brokerage** — the document-heavy renewal cycle 3. **Recruiting** — the source-to-place pipeline 4. **Support operations** — the ticket-to-resolution flow 5. **Software development** — process debt and the QA bottleneck For each, we'll show: - What the workflow looks like under the OLD model (humans coordinating, tools sprinkled) - What the workflow looks like under the AI-NATIVE model (agents executing, humans supervising) - Where the wedge sits — i.e., the one or two specific decisions that, once automated, cascade through the rest of the business - The metric that proves the rebuild worked ## What you're looking for as you read The same three signals across every example: 1. **High volume + existing rules + over-coordinated humans.** This is the step 1 criterion. Every case study below hits all three. 2. **Implicit knowledge made explicit.** Watch for the moment in each case study where some piece of tribal knowledge ("Sarah handles that one") becomes an explicit rule the agent can read. 3. **The human's role becomes more leveraged, not less important.** The recruiter stops being a data janitor and becomes a relationship closer. The support lead stops routing tickets and starts designing escalation logic. Watch for this transition in every case. If you can see those three signals in each industry, you can probably see them in your own industry. That's the whole point. ## A note on what this is not This is not a "here's how to use ChatGPT for your business" lesson. This is a lesson on what it takes to **restructure** a business so agents can run inside it. The central thesis (echoing Isenberg's writing on AI-native services): > An AI-native company is not a company that uses AI. It is a company > that has been rebuilt so AI can actually operate inside it. The case studies that follow describe rebuilds. Bolt-on chatbot implementations don't count. Custom GPTs labeled "Brand Voice Assistant" don't count. The bar is: **could a small team operate a business at 5-10× the productivity of a comparable incumbent because the workflow itself is machine-readable?** If yes, it's AI-native. If no, it's AI-assisted.38:T1799,# Case 1: Home services (HVAC, plumbing, electrical, cleaning) *(Illustrative scenario, not an actual case study.)* A 30-person HVAC company in suburban Phoenix. $4M ARR. Two dozen techs in the field, four dispatchers, two estimators, two AR clerks, a service manager, a marketing person, the owner. Phones ring all day. Most calls are 90 seconds of small talk followed by "can you come fix my AC tomorrow." The owner has been doing this for 22 years and his head is the operating system. This is the kind of company Isenberg's writing points at: boring, profitable, fragmented industries. Margins are 12-18%. The owner wants to retire. Nobody at the company has touched a Python interpreter in their lives. ## The old workflow Customer calls. Dispatcher writes the request on a paper form (yes, still). Walks it to the estimator. Estimator looks at the customer's address in QuickBooks to see if they're a prior customer. If they are, calls the tech who handled them last time to ask "what was this house like?" Tech doesn't answer because he's on a roof. Estimator quotes from memory plus a 10% pad. Schedule gets made by hand on a whiteboard. Tech shows up. Tech doesn't have the right part because nobody told inventory. Tech drives 20 minutes to the supply house. Tech finishes the job. Tech texts the dispatcher "done." Dispatcher updates QuickBooks. Three days later, the AR clerk emails an invoice. Two weeks later, the AR clerk emails a reminder. Six weeks later, the AR clerk calls. The owner takes 40% of his calendar to handle "exceptions" — i.e., everything the system didn't know how to do. Every step in that flow is a coordination tax. The technical work takes two hours. The administrative work takes six. ## The AI-native version Customer calls. The phone is answered by a voice agent that classifies the request (emergency vs scheduled, residential vs commercial, service vs install), pulls the customer's history from the unified record, checks tech availability against geographic clustering, and offers three time slots. The customer picks one. Behind the scenes, an agent has already: - Looked up the equipment at the address (from the prior service record) and pre-allocated the parts likely to be needed. - Generated a job brief for the tech: customer name, address, prior history, equipment model, common failure modes for that model, parts queued at the supply house. - Drafted a quote based on the equipment + job type + the explicit pricing rules in the spec. Quote requires owner approval if it's over $2,000 (the auto_approve threshold from step 06 of the previous lesson). - Sent the customer a confirmation with a calendar invite, an appointment-window text, and a "here's what to expect" PDF. Tech arrives. Tech's phone shows the job brief. Tech does the work. Tech speaks one paragraph into the app: "Replaced the capacitor, recharged refrigerant, customer asked about a maintenance plan." The agent turns that into: - An updated service record. - An automatic invoice draft (sent for owner approval if over threshold). - A flagged sales opportunity for the maintenance plan, queued for the marketing person's morning review. - A scheduled follow-up text 7 days later asking the customer for a review. AR clerk doesn't exist anymore. Or rather, she exists in a different role — she handles the 5% of invoices that can't auto-resolve (disputes, payment plan requests, payer changes), supervising the agent that handles the other 95%. The owner stops being the operating system. The dispatch whiteboard is gone. The "ask Sarah" parts of the business are written down as rules. The company runs. ## Where the wedge is The single highest-leverage automation is **classify-and-quote**. Once an incoming request can be classified (emergency vs scheduled, residential vs commercial, service vs install) and a draft quote can be generated against explicit pricing rules, the rest of the business reorganizes around it: - Dispatch becomes a constraint-solver, not a phone-based whiteboard. - The tech's job brief becomes a deterministic output of the classification + customer history. - The AR cycle becomes a state machine the agent runs. Without classify-and-quote, every other automation is bolt-on. With it, the workflow has a spine. ## The metric that proves it worked Three numbers, none of them "hours saved": 1. **Time from call to scheduled appointment**: was 18 hours (call-to-callback-to-quote-to-confirmation). Target: under 2 minutes. 2. **First-time-fix rate**: was 71% (tech arrives without the right part 29% of the time). Target: 92%+ (parts pre-allocated based on history). 3. **Revenue per technician per month**: was $42,000. Target: $58,000+ (less driving, faster scheduling, more jobs per day). The AI-native version of this company runs with 12 people instead of 30 and clears the same revenue. That's not a productivity bump. That's a different company. The shape Isenberg's writing keeps pointing at: small teams. Narrow markets. Proprietary workflows. High automation. High trust. Clear customer pain. Boring category. Beautiful margins. ## What this case study teaches Three observations that generalize: - **The administrative work is the cost.** The technical work (fixing the AC) was always the easy part. What killed margins was the coordination around it. AI-native rebuilds attack the coordination, not the craft. - **The owner's head is the bottleneck.** Every old service business has an owner who knows everything and can't be cloned. AI-native rebuilds force the owner to write down what he knows — not for documentation's sake, but because the agent needs it. - **Pricing rules first, everything else second.** Every automation downstream depends on the agent being able to quote. If you can't encode the pricing logic, you can't go AI-native. If you can, everything else falls into place. In the next case (insurance brokerage), the same three patterns repeat with different surface area.39:T1847,# Case 2: Insurance brokerage (commercial lines, small business) *(Illustrative scenario, not an actual case study.)* A 60-person commercial insurance brokerage. $12M revenue. Specializes in policies for small businesses (restaurants, contractors, retail stores). Renewal cycle every 12 months. The job is to gather the customer's data, compare quotes from 8-12 carriers, flag risk exposures, present options to the customer, place the policy, and service it for the year. Then do it again. The work is 90% structured. Forms. Documents. Comparisons. Policy language. Premium calculations. Renewal deadlines. The 10% that isn't structured is the actual broker-customer conversation: "your business has changed, here's what that means for your coverage." That 10% is where the real value sits. The other 90% is where the margin goes to die. ## The old workflow Renewal is 90 days out. An account manager pulls up the customer's current policy. Emails the customer asking for updated information (payroll counts, square footage, prior claims, new business lines). Customer doesn't reply. Account manager follows up. Customer replies in fragments across three emails and a phone call. Account manager hand-fills the data into the carrier comparison tool. Tool spits out 8 quotes. Account manager compares them in a spreadsheet. Drafts a client memo. Sends to the broker for review. Broker tweaks. Broker meets with the customer. Customer asks about coverage gaps. Broker goes back to the carriers for clarification. Two more weeks pass. Policy gets placed three days before expiration. Account manager sets up the renewal calendar entry for next year. Account manager also services the policy mid-year when there's a claim, a coverage change, or a billing question. A senior account manager handles maybe 80 accounts and works 55 hours a week. Most of those hours are NOT spent advising the customer. They are spent moving information between tools, remembering details, chasing carriers, and writing the same email in slightly different forms. ## The AI-native version The agent owns the data-gathering and the comparison. Specifically: - **Pre-renewal intake**: 90 days out, the agent emails the customer with a structured questionnaire pre-filled with everything known about the business. Customer reviews and corrects. Agent flags changes (payroll up 30%, new business line) for the broker. - **Carrier outreach**: agent submits the application to all relevant carriers automatically. Tracks responses. Flags questions back to the broker only when the carrier asks something a human needs to answer. - **Comparison memo**: agent generates a structured comparison of the 8-12 quotes that come back. Highlights coverage gaps. Calls out cases where the cheapest option isn't the right one. Memo goes to the broker for review. - **Customer meeting prep**: agent prepares a one-page brief for the broker covering changes year-over-year, gaps to discuss, upsell opportunities (cyber coverage just got cheap), and competitor activity in the customer's industry. - **Policy placement**: once the customer picks a carrier, the agent files the paperwork, schedules the renewal calendar entry, and sets up the billing. The broker does the customer meeting, the judgment calls on coverage tradeoffs, and the relationship work. The account manager becomes a supervisor of the agent — handling exceptions, training the agent on edge cases, and reviewing flagged decisions before they go out. A 60-person brokerage becomes a 25-person brokerage running the same book. The senior brokers stop spending 30 hours a week on data movement and start spending 30 hours a week on customer relationships. Their close rate goes up. Their account count per broker doubles. ## Where the wedge is Two automations cascade through the whole business: 1. **Structured intake**. If you can't get the customer's data into structured form without a human doing it, nothing else automates. The first investment is a renewal questionnaire that's pre-filled, validated, and a quarter as long as the carrier's official form. 2. **Quote-to-comparison generation**. Once you have the data, the agent can submit it to all carriers and turn the 8-12 quote PDFs back into a structured comparison. This is the single most-time-consuming thing the account manager does. Eliminating it is the difference between a 10% margin and a 35% margin. Everything else (policy service, billing, renewal scheduling) is downstream. ## The metric that proves it worked Three numbers: 1. **Time from intake start to client meeting**: was 35 days (because nobody could find time). Target: 8 days. 2. **Account-manager-to-broker ratio**: was 3:1 (account managers doing data work). Target: 1:2 (account managers supervising agents, more brokers because each is more productive). 3. **Customer retention rate**: was 86% (customers churn when the renewal feels mechanical). Target: 94%+ (the customer meeting is now substantive, not transactional). The same logic applies to legal services, accounting firms, compliance shops, and healthcare admin. Document-heavy, rule-based, deadline-driven, relationship-finished. Every one of those industries has the same 90/10 split between structured work and judgment. Every one is ripe. ## What this case study teaches - **Document-heavy industries are the wedge.** If a business runs on forms, contracts, comparisons, and structured comparisons, agents can swallow 80% of it. Insurance, mortgages, tax prep, HR compliance, accounting, legal intake — all the same shape. - **The customer experience changes shape.** Customers in the old model talked to their broker once a year, the rest was emails about paperwork. In the AI-native model, the broker talks to the customer about substantive coverage decisions, and the paperwork is invisible. The customer feels more served, with less broker time. - **The account-manager role transforms, doesn't disappear.** The old account manager was a data janitor. The new account manager is an agent supervisor. Same person, more leveraged work, higher compensation, lower headcount.3a:T1634,# Case 3: Recruiting firm (technical roles, $250K+) *(Illustrative scenario, not an actual case study.)* A 25-person tech recruiting firm. $8M revenue. Places senior engineers, engineering managers, and CTOs at venture-backed startups. Average placement fee: $40K. Average placement cycle: 3-4 months. Recruiters earn commission on closes. The job is 40% sourcing (finding candidates), 30% screening (initial calls), 20% client management (interfacing with the hiring company), and 10% closing (the actual offer and negotiation). The recruiting-industry version of the AI-native thesis (echoing Isenberg's writing on AI-native services): > Agents source candidates, enrich profiles, compare against role > requirements, draft outreach, summarize interviews, check > references, update pipelines, and alert humans when a candidate > is unusually strong. The recruiter stops being a data janitor and > becomes a relationship closer. ## The old workflow The client posts a job. Recruiter reads the JD. Recruiter logs into LinkedIn Recruiter and searches. Spends three hours scrolling profiles. Adds 50 candidates to a "to outreach" list in Notion. Drafts an outreach email per candidate (each one slightly tweaked to feel personal). Sends. Gets 3 replies. Schedules screening calls. Does the screening calls. Writes up notes in the ATS (when she remembers to). Sends the strongest 5 candidates to the client. Client picks 2 to interview. Interviews happen. Client picks one. Reference checks. Offer. Negotiation. Close. Move on to the next job, which has been sitting unopened in the recruiter's inbox for three weeks. The same recruiter works on 4-6 active searches at a time. Each search takes 60-80 hours. Most of those hours are not negotiation, not relationship work, not judgment. Most of those hours are sourcing-screening-notetaking-updating, in some combination. ## The AI-native version The agent owns the entire top-of-funnel: - **Sourcing**: agent reads the JD, generates the candidate profile, and searches across LinkedIn, GitHub, conference speaker lists, prior placement databases, and the recruiter's own network graph. Surfaces 50-200 candidates per search. - **Enrichment**: agent enriches each candidate with their current company, prior roles, code repos, conference talks, geographic flexibility signals, compensation signals, and any signal that they're open to a move (Twitter post about burnout, last LinkedIn update, prior moves at similar tenure). - **Outreach**: agent drafts a personalized message per candidate. The recruiter reviews and either approves or tweaks before send. (This is an "approval where judgment matters" case — the outreach has the recruiter's name on it, so she gets to gate it.) - **Screening prep**: agent prepares a one-page brief for every inbound reply: candidate's history, talking points, likely objections, comp anchor, expected questions. - **Post-call summary**: recruiter takes the call. Agent listens via transcription (recorded with consent). Generates the structured summary, updates the ATS, scores the candidate against the JD rubric, and flags interview readiness. - **Client memo**: agent generates the "top 5 candidates" memo for the client, structured the way the client likes (some clients want a single-page summary; some want a deep packet; the agent learns). - **Reference checking**: agent drafts reference outreach, schedules calls, summarizes the conversations, and flags any yellow flags. The recruiter does the screening conversation, the client relationship, the offer negotiation, and the close. The agent does everything else. A senior recruiter who used to run 4-6 searches at a time can now run 12-18. The firm's revenue per recruiter triples. The firm goes from 25 people to 15 (the data-janitor roles vanish) and revenue goes UP. Net margin moves from 18% to 42%. ## Where the wedge is The big-rock automation is **screening summary + ATS update**. Recruiters write half their hours into the ATS. If the agent does that automatically from the call, every other piece of the workflow gets faster: - Outreach quality goes up because there's better data on the candidate. - Client memos get generated cleanly because the ATS is actually current. - Pipeline reviews stop being archaeology. The second big-rock is **personalized outreach at volume**. The old recruiter sent 50 emails a week. The agent-supervised recruiter sends 250 a week with higher reply rates because each one is properly personalized. ## The metric that proves it worked 1. **Reply rate to cold outreach**: was 6% (recruiter writing tired emails at 4pm). Target: 14%+ (every email is properly personalized; recruiter just approves). 2. **Searches per recruiter per quarter**: was 5. Target: 15-20. 3. **Time-to-first-submit**: was 18 days (sourcing took forever). Target: 4 days. ## What this case study teaches - **Top-of-funnel is the agent's home turf.** Anywhere the work is "find candidates / leads / accounts / documents and enrich them," agents win immediately. The recruiter's job becomes a relationship job, which is what good recruiters always wanted it to be. - **Personalization at volume is the unlock.** The old constraint was "you can't write 250 personalized emails a week." Agents remove that constraint. The recruiter still writes the personality; the agent fills in the facts. - **The ATS-as-bottleneck problem is everywhere.** Every customer- facing business has this in some shape (CRM data debt, customer history scattered across tools, "the truth lives in someone's inbox"). Solving it is half the AI-native rebuild.3b:T422,# four industries. each one is "AI-native rebuildable" in principle. # but which one wedges in fastest with the smallest team? industries = { "A": { "name": "Boutique law firm (M&A advisory)", "volume": "low (10 deals/year)", "rules": "complex, mostly tacit", "outcome": "high-stakes, irreversible", }, "B": { "name": "Bookkeeping for SMBs", "volume": "high (300+ clients/month)", "rules": "explicit (GAAP + tax code)", "outcome": "structured, recurring", }, "C": { "name": "Public-relations agency", "volume": "medium (40 active campaigns)", "rules": "taste-driven, relationship-heavy", "outcome": "subjective, narrative", }, "D": { "name": "Investment banking (capital markets)", "volume": "low (per deal)", "rules": "regulated, judgment-dense", "outcome": "high-stakes, brand-risky", }, } for k, v in industries.items(): print(f"{k}: {v['name']:35} vol={v['volume']:20} rules={v['rules']}") 3c:T20f9,# Case 4-5: Support ops + software dev — and the incumbent trap *(Illustrative scenarios, not actual case studies.)* We've walked through three rebuilds where a small AI-native team can outrun a larger incumbent. Two more, briefly, before we get to the real lesson of this chapter: **why the incumbents can't catch up**. ## Case 4: Support operations A 40-person SaaS support team for a B2B product. Tickets flow in through email, chat, intercom, and a community forum. Median resolution time is 4.5 hours. CSAT is 4.1. The support manager spends Sundays running pivot tables to figure out which agents are slow and which categories of tickets spike. AI-native version: a triage agent reads every inbound, classifies it (bug / billing / feature-request / how-to), pulls the customer account context, drafts the response, and either resolves the ticket (for clearly-resolvable cases) or routes it to the right human with a pre-drafted reply and a one-line summary. The support manager builds dashboards from structured ticket data instead of hand-coding categories. The 40-person team becomes 12 people doing higher-leverage work (writing canned responses, designing escalation logic, training the agent, talking to angry enterprise customers). Resolution time drops to under an hour. CSAT goes to 4.6. The product team gets better signal because every ticket is properly categorized. The wedge: **classification + draft response**. Once those two steps are agent-owned, the entire support workflow reorganizes around them. ## Case 5: Software development (the process-debt case) An under-credited point that's been circulating in the AI-native discourse: > Process debt hits hard in software dev. Using AI to code faster > just makes you hit the QA bottleneck faster. Until humans stop > manually running the tests, the org isn't AI-native yet. This is the most underrated thing in the AI-native discourse. Every dev team has been told "use Copilot, ship faster." They do. Code velocity goes up. Then the bottleneck moves: from code generation to code review, then to QA, then to deployment, then to incident response. The AI-native software team isn't the one that writes code with AI. It's the one whose **entire SDLC** — the pipeline from "idea" to "in prod" — has been rebuilt so agents can operate inside every step. That looks like: - **PR review**: an agent reviews every PR for the obvious things (typing, naming, test coverage, perf regressions) before the human reviewer sees it. Human reviewer only sees the 20% of PRs that need taste-level judgment. - **Test generation**: an agent generates the test cases from the PR diff + prod traffic patterns + prior bug history. Coverage goes up without the human writing tests. - **Deployment gates**: an agent runs the deployment checklist, monitors the canary, decides whether to roll back, and pages the human only when something is genuinely off. - **Incident response**: an agent collects the logs, traces, and metric anomalies for any incident and drafts the postmortem skeleton. The human writes the "what we'll change" section. A 50-person engineering org becomes a 20-person org shipping the same surface area, because the agent absorbs everything that was process tax. The 20 people stop being a code factory and become a system-design team. ## The incumbent trap Every case study above describes a 5-15-person AI-native team outperforming a 40-100-person incumbent. The obvious question is: **why don't the incumbents just do the same thing?** The answer (and the reason Isenberg's writing keeps returning to this point): **process debt**. > The hard part is that incumbents are full of old process debt. > Their data is messy. Their policies conflict. Their teams > protect turf. Their workflows were built around headcount. > Their software stack is stitched together with duct tape and > quarterly planning rituals. Their operating system assumes > humans are the default processors of information. A 200-person HVAC company can't just "go AI-native." To do it, they would need to: 1. **Clean the data.** Customer records are scattered across QuickBooks, a paper filing cabinet, three dispatchers' heads, and one tech's text messages. Cleaning that takes 6-12 months and no one wants to fund it. 2. **Write down the policies.** The owner's head IS the policy. Writing it down is months of meetings he doesn't have time for, and arguments about which version is the "real" policy. 3. **Restructure the team.** The four dispatchers + two AR clerks + two estimators don't have AI-native roles. They have to be reskilled or replaced. That's a political knife-fight. 4. **Replace the software stack.** The CRM, the dispatch whiteboard, QuickBooks, and the paper forms have to be replaced with a single integrated system that agents can read and write to. 5. **Build the eval and feedback loops.** Once agents are in the workflow, the company needs to measure their outputs, catch their mistakes, and improve the prompts. Nobody on the team knows how to do this. The new AI-native company doesn't have any of this debt. They start clean. They wrote the policies BEFORE they hired the dispatchers. They built the data model BEFORE they took the first customer. They designed the workflow assuming agents would run it. Their software stack is one app, not nine. That's the asymmetry. The new entrant doesn't have to undo anything. The incumbent has 22 years of "ask Sarah" to dismantle before they can even start. ## What this case study teaches (and why theory matters) - **The bottleneck isn't AI access — it's organizational legibility.** Every company has access to the same models. The ones who win are the ones who restructured the company so the models have something to work with. - **Process debt compounds in the wrong direction.** Every year an incumbent doesn't pay down process debt, their AI-native competitor gets a year of compounding advantage. By the time the incumbent realizes the gap, it's too late. - **The strategic question for a founder is "what's process-debt- free that I could rebuild from scratch?"** Pick an industry where the incumbents are 30+ years old, the workflow is document-heavy, and the customer pays for an OUTCOME. That's where the next decade's wealth is going. This is why theory matters in this course. You can drill on Python syntax forever and not see what to BUILD with it. The reading is how you find the wedge. The code is how you execute on it. ## The one real anchor case The five industries above are illustrative. Before this lesson ends, here is the one case study in this chapter that has receipts. **Klarna's 2024-2025 customer service rebuild** is the most public, documented agent-native deployment to date. The OpenAI case study and Sebastian Siemiatkowski's May 2025 walk-back are both part of the same story: an aggressive AI-first rebuild, real productivity gains (the AI assistant handled the equivalent workload of roughly 700 full-time agents in its first month), real quality regressions (customer-facing quality dropped enough that Siemiatkowski publicly admitted the company had cut human agents too aggressively), and a public correction (Klarna began re-hiring human agents for cases the AI couldn't handle well). The Klarna story has receipts. The five rebuilds above don't. They are scenarios in the shape of how an agent-native company could go, informed by patterns visible in real deployments like Klarna and Cresta. They are not documentation of companies that have shipped these systems. > Read the Klarna section twice for every illustrative scenario you > read once. The illustrative scenarios are useful for pattern > recognition. The Klarna story is what actually happens when you > ship one. You'll see the Klarna case discussed in more detail in ch00 (how the market is shifting) and ch24 (debugging output — the specific failure modes that caused the walk-back). Both treatments name the gains AND the regressions, because the honest version of this story is the one that holds both at once. The remaining steps of this lesson are interactive. They take the case-study framework and apply it to a structured "process debt audit" you can run against a real business. By the end you'll have a function you can paste into a notebook and use on your own job or your own startup idea.3d:T525,hvac_inc = { "name": "HVAC Inc", "age_years": 22, "data_scattered_across_tools": 6, "tacit_knowledge_pct": 65, "paper_processes": 2, "headcount_per_revenue_million": 8, "documented_workflows_pct": 15, } startup_co = { "name": "StartupCo", "age_years": 1, "data_scattered_across_tools": 2, "tacit_knowledge_pct": 30, "paper_processes": 0, "headcount_per_revenue_million": 4, "documented_workflows_pct": 80, } def process_debt_score(company): score = 0 if company.get("age_years", 0) > 10: score += 25 if company.get("data_scattered_across_tools", 0) >= 5: score += 20 if company.get("tacit_knowledge_pct", 0) > 50: score += 20 if company.get("paper_processes", 0) > 0: score += 15 if company.get("headcount_per_revenue_million", 0) > 7: score += 10 if company.get("documented_workflows_pct", 100) < 30: score += 10 if score <= 20: verdict = "AI-native ready" elif score <= 50: verdict = "manageable debt" elif score <= 80: verdict = "heavy debt" else: verdict = "incumbent trap" return {"score": score, "verdict": verdict} print(f"HVAC Inc: {process_debt_score(hvac_inc)}") print(f"StartupCo: {process_debt_score(startup_co)}") 3e:T484,candidates = [ {"name": "Boutique law firm", "volume_per_week": 2, "rules_explicit": False, "outcome_structured": False, "incumbent_avg_age_years": 30}, {"name": "Insurance brokerage", "volume_per_week": 200, "rules_explicit": True, "outcome_structured": True, "incumbent_avg_age_years": 35}, {"name": "PR agency", "volume_per_week": 40, "rules_explicit": False, "outcome_structured": False, "incumbent_avg_age_years": 15}, {"name": "Bookkeeping for SMBs", "volume_per_week": 300, "rules_explicit": True, "outcome_structured": True, "incumbent_avg_age_years": 18}, {"name": "VC investing", "volume_per_week": 1, "rules_explicit": False, "outcome_structured": False, "incumbent_avg_age_years": 25}, ] def score_candidate(c): s = 0 if c["volume_per_week"] >= 100: s += 30 if c["rules_explicit"]: s += 25 if c["outcome_structured"]: s += 25 if c["incumbent_avg_age_years"] >= 20: s += 20 return s def pick_industry(candidates): return max(candidates, key=score_candidate)["name"] print(f"best: {pick_industry(candidates)}") 3f:T647,# A runbook a junior can execute lives in the repo Layer 4 is why this lesson exists. The harness can edit files, run commands, and ship a dispatch change. Anything that can change the world needs a way to undo it — written down next to the harness, not in a wiki tab someone has to interpret while the batch is still failing. Run the editor. Two artifacts, same nickname. The wiki line is a page. The dict is a runbook: a signal to read, a threshold that means rollback, a named human if the decision needs one, and a path in the repo for the record. That is the whole job. Detect. Decide rollback versus continue. Name a human if you cannot execute the decision alone. Write the record back. A junior on the on-call seat should be able to follow it from the checkout without inventing a process. This is the ops role's failure path — one seat, one workflow. Not a company-wide rebuild. ## What this lesson is NOT - Not a war story. The numbers are quiet on purpose. - Not a page that says "stay calm" and then stops. - Not a hiring pitch. What it IS: the failure path as data, the same way lesson 02 made the happy path a spec. Rollback is the point. If the runbook cannot tell a junior when to undo the last ship, it is still a wiki page. ## What you'll build `execute_runbook(signals, runbook)` — read the signal, return rollback / continue / escalate, attach the named human only when escalate fires, and produce the writeback record a later checkout can grep. The runbook you write is the one you would want sitting in `incidents/` the next time the nightly batch misses its threshold.40:T7f6,# Detect, decide, name a human, write it back Four fields. That is the runbook. 1. **Detect.** Which signal, and from where. Here it is `error_rate` on the nightly harness batch — the same loop you built in lesson 01, now missing its threshold. 2. **Decide.** Rollback if the signal is at or above the line. Continue if it is under. No third mood called "wait and see" unless the runbook wrote that mood down as continue. 3. **Named human.** A seat, not a channel. `release-owner` is a person who can unblock a rollback. "The team" is not a page target. 4. **Writeback.** A path in the repo. The decision becomes a line in `incidents/log.jsonl` so the next checkout can see what ran. Slack is not the record. Run the editor. Three quiet incidents, one rule. | id | error_rate | rollback_blocked | decision | |---|---|---|---| | INC-041 | 0.12 | no | **rollback** | | INC-042 | 0.03 | no | **continue** | | INC-043 | 0.15 | yes | **escalate** | INC-043 is the only one that names a human. The signal says rollback, but rollback cannot run (last-good tag missing, lock held, whatever the runbook marked as blocked). The junior does not invent a workaround. They page `release-owner` and write that down. ## Why rollback is the point Continue is allowed. It is just not the default once the signal crosses the line. The expensive mistake at 3am is shipping past a threshold because the wiki said "use your judgment." Judgment is what you do when the runbook has no rule. If the rule exists, you execute it. Escalate is not a vibe. It is the branch where the written action cannot run, so a named human has to. ## What the next steps drill - Predicting the three decisions from the table (step 4) - Filling the threshold comparison from the runbook (step 5) - Replacing a wiki string with the four fields (step 6) - Replacing "the team" with the named human (step 7) - Writing `execute_runbook` so the writeback record falls out of the decision (step 8) - Running three incidents through it (step 9)42:I[93250,["/_next/static/chunks/2rjtqver_q2gs.js","/_next/static/chunks/0mg7io3h2u8wq.js","/_next/static/chunks/2axu7w_5i8n32.js","/_next/static/chunks/3he5zzx1k7c6r.js","/_next/static/chunks/0h0bavt00zz2v.js","/_next/static/chunks/3s-oul0007que.js"],"IconMark"] 41:T451,RUNBOOK = { "detect": {"signal": "error_rate", "rollback_if_at_least": 0.08}, "named_human": "release-owner", "writeback": {"path": "incidents/log.jsonl"}, } incidents = [ {"id": "INC-041", "error_rate": 0.12, "rollback_blocked": False}, {"id": "INC-042", "error_rate": 0.03, "rollback_blocked": False}, {"id": "INC-043", "error_rate": 0.15, "rollback_blocked": True}, ] def execute_runbook(signals, runbook): detect = runbook["detect"] if signals.get("rollback_blocked"): decision = "escalate" elif signals[detect["signal"]] >= detect["rollback_if_at_least"]: decision = "rollback" else: decision = "continue" actor = runbook["named_human"] if decision == "escalate" else "runbook" return { "id": signals["id"], "decision": decision, "signal": signals[detect["signal"]], "actor": actor, "artifact": runbook["writeback"]["path"], } for inc in incidents: rec = execute_runbook(inc, RUNBOOK) print(f"{rec['id']} {rec['decision']} actor={rec['actor']} artifact={rec['artifact']}") 1c:[["$","$L24",null,{"payload":{"catalog":"Architecting an AI-native workflow — a 5-step playbook in code (step 4/9) · agent harnesses · promptdojo","byPath":{"developer":"Architecting an AI-native workflow — a 5-step playbook in code (step 4/9) · agent harnesses · promptdojo","operations":"Architecting an AI-native workflow — a 5-step playbook in code (step 4/9) · agent harnesses · promptdojo"}}}],["$","script",null,{"type":"application/ld+json","dangerouslySetInnerHTML":{"__html":"$25"}}],["$","$L26",null,{"tree":{"toc":{"version":"0.1.0","generatedAt":"1970-01-01T00:00:00.000Z","chapters":[{"number":0,"slug":"before-you-build","title":"from worker to builder","blurb":"stop doing repeated work by hand. this chapter is the map: the builder loop, old workplace deliverables turned into site artifacts, and the reusable tool card. if you are starting here, those moves are the lesson. if you already ran a studio, you already used the loop.","status":"live","lessonCount":10,"stepCount":14,"liveLessonCount":10,"liveStepCount":14,"estMinutes":74,"xpTotal":36},{"number":1,"slug":"read-the-script","title":"read the script — your first code-reading lab","blurb":"ai hands you small scripts. this lab covers the three reads that matter: what the names hold, whether the function actually returns, and which branch of the if-chain really fires. if you are starting here, this labels the reads. if you already ran a studio, you already wrote these.","status":"live","lessonCount":3,"stepCount":24,"liveLessonCount":3,"liveStepCount":24,"estMinutes":21,"xpTotal":78},{"number":2,"slug":"read-the-data-shapes","title":"read the data shapes — the json ai just dumped","blurb":"every api response, config file, and llm reply is lists and dicts nested in a tree. read the shape on sight, walk it with a loop, and catch the wrong-layer bug ai loves to ship.","status":"live","lessonCount":3,"stepCount":24,"liveLessonCount":3,"liveStepCount":24,"estMinutes":23,"xpTotal":80},{"number":3,"slug":"read-the-failure","title":"read the failure — cursor wrote this and crashed","blurb":"when python crashes, it tells you exactly what happened and where. most non-engineers panic at the wall of text — and ai 'fixes' the crash by hiding it. learn to read the failure, then catch only what's worth catching.","status":"live","lessonCount":3,"stepCount":24,"liveLessonCount":3,"liveStepCount":24,"estMinutes":24,"xpTotal":83},{"number":4,"slug":"read-the-pipeline","title":"read the pipeline — files in, api calls out","blurb":"every real script reads a file or calls an api — usually both. learn the with-block, the status-code families, and the retry rules: the seatbelts ai forgets to put on.","status":"live","lessonCount":3,"stepCount":24,"liveLessonCount":3,"liveStepCount":24,"estMinutes":26,"xpTotal":83},{"number":7,"slug":"mutation-and-state","title":"mutation — why your code mysteriously breaks","blurb":"when a list inside a function changes the list outside the function, that's mutation. ai does this constantly without flagging it, and it's the bug class that takes the longest to find.","status":"live","lessonCount":2,"stepCount":9,"liveLessonCount":2,"liveStepCount":9,"estMinutes":10,"xpTotal":32},{"number":13,"slug":"llm-apis","title":"llm apis — talking to claude and openai","blurb":"every ai feature you ship eventually calls a model api. learn the messages pattern, how to read the response, and the four lines ai writes every single time.","status":"live","lessonCount":4,"stepCount":27,"liveLessonCount":4,"liveStepCount":27,"estMinutes":45,"xpTotal":87},{"number":14,"slug":"structured-output","title":"structured output — making the model return json","blurb":"free-form text breaks every pipeline. learn the schema-first pattern ai uses to get reliable json back, validate it with pydantic, and catch the model's lies before they hit prod.","status":"live","lessonCount":3,"stepCount":25,"liveLessonCount":3,"liveStepCount":25,"estMinutes":38,"xpTotal":80},{"number":15,"slug":"mcp","title":"mcp — the model context protocol","blurb":"mcp is the new standard for plugging tools and data sources into ai agents. learn what an mcp server actually is, how claude code lists tools, and why this is replacing one-off integrations everywhere.","status":"live","lessonCount":3,"stepCount":26,"liveLessonCount":3,"liveStepCount":26,"estMinutes":40,"xpTotal":85},{"number":16,"slug":"agent-loops","title":"agent loops — tool_use and the request/tool/respond cycle","blurb":"an agent isn't magic. it's a while loop. learn the actual cycle claude code, cursor, and every other agent uses: model returns tool_use, you run the tool, you send the result back, repeat until end_turn.","status":"live","lessonCount":6,"stepCount":48,"liveLessonCount":6,"liveStepCount":48,"estMinutes":71,"xpTotal":154},{"number":17,"slug":"git-and-github","title":"git and github cli — the ai builder's actual workflow","blurb":"cursor and claude code commit on your behalf. reading those commits — and undoing the bad ones — is your job. learn the three-state model, the commands you'll run every day, and what `gh` does that `git` can't.","status":"live","lessonCount":3,"stepCount":24,"liveLessonCount":3,"liveStepCount":24,"estMinutes":36,"xpTotal":79},{"number":18,"slug":"secrets-and-env","title":"secrets — .env, api keys, and what not to commit","blurb":"ai ships keys to github all the time. learn the .env pattern, why os.getenv is non-negotiable, what to do when a key leaks, and the gitignore lines you need on day one.","status":"live","lessonCount":2,"stepCount":16,"liveLessonCount":2,"liveStepCount":16,"estMinutes":16,"xpTotal":58},{"number":19,"slug":"prompting","title":"prompting ai coding tools","blurb":"an AI coding tool writes and edits with you — Cursor is one brand, Claude Code is another. the difference between a one-shot session and a four-hour spiral is almost always the first prompt.","status":"live","lessonCount":5,"stepCount":36,"liveLessonCount":5,"liveStepCount":36,"estMinutes":59,"xpTotal":118},{"number":20,"slug":"agent-traces","title":"reading agent traces and telemetry","blurb":"when an agent fails, the trace tells you exactly where. learn to read tool calls, tool results, and stop reasons — the json breadcrumbs every agent leaves behind.","status":"live","lessonCount":3,"stepCount":25,"liveLessonCount":3,"liveStepCount":25,"estMinutes":30,"xpTotal":88},{"number":21,"slug":"evals","title":"test the agent before you trust it","blurb":"same input, check the output, pass or fail. don't ship on a demo that felt right.","status":"live","lessonCount":5,"stepCount":34,"liveLessonCount":5,"liveStepCount":34,"estMinutes":57,"xpTotal":112},{"number":22,"slug":"context-and-retrieval","title":"context and retrieval — feeding the model real data","blurb":"rag without the overengineering. chunking, embeddings, vector search, and the small set of patterns that make a model answer from your data instead of its training set.","status":"live","lessonCount":5,"stepCount":44,"liveLessonCount":5,"liveStepCount":44,"estMinutes":75,"xpTotal":144},{"number":23,"slug":"production-tradeoffs","title":"production tradeoffs — cost, latency, quality","blurb":"the three numbers every shipped llm feature lives or dies by. token math, caching, streaming, batching, and the small set of decisions that move the product more than a model swap ever will.","status":"live","lessonCount":4,"stepCount":33,"liveLessonCount":4,"liveStepCount":33,"estMinutes":57,"xpTotal":111},{"number":24,"slug":"debugging-output","title":"debugging broken ai output","blurb":"when the model lies to your customer. the methodology for narrowing down what went wrong, the four most-common breakage classes, and the discipline that separates 'we shipped a fix' from 'we blamed the model and shrugged'.","status":"live","lessonCount":4,"stepCount":34,"liveLessonCount":4,"liveStepCount":34,"estMinutes":61,"xpTotal":112},{"number":25,"slug":"capstone","title":"mid-path build — ship the CLI agent","blurb":"wire it all together. the prompt, the call, the validation, the trace, the eval, the MCP tool. a path checkpoint, not the end of the course: the smallest end-to-end llm feature you could ship to a real user. retrieval and prompt-cache cost work live in later chapters — extend this build with them when you scale past the demo input set.","status":"live","lessonCount":7,"stepCount":62,"liveLessonCount":7,"liveStepCount":62,"estMinutes":100,"xpTotal":219},{"number":26,"slug":"agent-harnesses","title":"agent harnesses — the layer between you and the raw api","blurb":"claude code, cursor, aider, codex cli — they're all the same four layers wrapped around the same model api. learn what those layers are, what each adds, and what you'd build yourself if you had to. when the harness changes the world, the rollback lives in the repo — a runbook a junior can execute at 3am.","status":"live","lessonCount":5,"stepCount":37,"liveLessonCount":5,"liveStepCount":37,"estMinutes":69,"xpTotal":119},{"number":27,"slug":"ai-image-generation","title":"ai image generation — from prompt to production asset","blurb":"the 2026 image model landscape, the prompts that work, and the pipeline that turns one good idea into a hundred ready-to-ship images. nano banana 2 for volume, nano banana pro for fidelity, flux, midjourney, ideogram, gpt-image-2. when each wins and what they cost.","status":"live","lessonCount":3,"stepCount":24,"liveLessonCount":3,"liveStepCount":24,"estMinutes":60,"xpTotal":67},{"number":28,"slug":"ai-video-generation","title":"ai video generation — omni, veo 3.1, sora, and the second wave","blurb":"video is the hardest content type to generate, the most expensive, and the most strategically interesting. learn the 2026 model lineup, the camera-control patterns that separate slop from craft, and the cost math that decides whether your idea is viable.","status":"live","lessonCount":3,"stepCount":23,"liveLessonCount":3,"liveStepCount":23,"estMinutes":50,"xpTotal":61},{"number":29,"slug":"programmatic-design","title":"programmatic design — code-driven video and the new design pipeline","blurb":"ai generates raw assets; code stitches them into something shippable. hyperframes, remotion, claude design — when each tool wins, how they combine, and the data-driven workflows that turn one template into a hundred videos.","status":"live","lessonCount":3,"stepCount":24,"liveLessonCount":3,"liveStepCount":24,"estMinutes":46,"xpTotal":66},{"number":30,"slug":"harness-engineering","title":"harness engineering — the discipline behind the model","blurb":"every coding agent is a model plus a harness. the model is bought; the harness is engineered. learn the craft: how to ratchet rules from failures, fight context rot, design long-horizon loops, wire hooks as enforcement, and read the haas shift that's reshaping what you build vs buy.","status":"live","lessonCount":6,"stepCount":52,"liveLessonCount":6,"liveStepCount":52,"estMinutes":126,"xpTotal":143},{"number":31,"slug":"intro-to-terminal","title":"intro to terminal — the text way to drive your computer","blurb":"the terminal is a text box: type a name, press enter, the computer does it. by the end you can move around your files, make folders, and read files without the mouse. every later tool chapter assumes this.","status":"live","lessonCount":3,"stepCount":23,"liveLessonCount":3,"liveStepCount":23,"estMinutes":26,"xpTotal":50},{"number":32,"slug":"intro-to-claude-cli","title":"intro to claude cli — the door to real building","blurb":"you've used claude in a chat window. the claude cli is the same model with its hands on your actual files. this chapter installs it, signs you in, and runs your first real command. by the end you've watched an ai read, plan, and change things on your machine, and you know when to reach for the cli instead of the chat box.","status":"live","lessonCount":3,"stepCount":23,"liveLessonCount":3,"liveStepCount":23,"estMinutes":32,"xpTotal":48},{"number":33,"slug":"intro-to-codex-cli","title":"intro to openai codex cli — a second tool in the kit","blurb":"you know the claude cli. the openai codex cli does the same job, an ai working in your terminal on your real files, with a different company behind it. this chapter installs it, signs you in, and runs your first command. most of what you already know carries straight over, so this chapter is mostly about what is different and when to reach for which.","status":"live","lessonCount":3,"stepCount":23,"liveLessonCount":3,"liveStepCount":23,"estMinutes":32,"xpTotal":45},{"number":34,"slug":"team-skills","title":"claude skills for teams — playbooks your whole team shares","blurb":"a claude skill is a packaged set of instructions — your team's playbook — that claude loads when it's relevant, so nobody has to re-explain it. this chapter is for people who manage teams. it covers what a skill is, how a team shares and provisions skills, real examples for hr, legal, and ops work, when a skill beats a one-off prompt, and the governance you need before any skill touches real work.","status":"live","lessonCount":4,"stepCount":28,"liveLessonCount":4,"liveStepCount":28,"estMinutes":41,"xpTotal":60},{"number":35,"slug":"dataframes-numpy-pandas","title":"dataframes with numpy and pandas","blurb":"tables are the working surface of applied ml. learn rows, columns, missing values, joins, aggregates, and the dataframe habits ai-generated notebooks assume.","status":"live","lessonCount":6,"stepCount":42,"liveLessonCount":6,"liveStepCount":42,"estMinutes":43,"xpTotal":156},{"number":36,"slug":"sql-for-ml-datasets","title":"sql for ml datasets","blurb":"most training data starts in a database. learn the select, join, filter, aggregate, and leakage traps that decide whether a model is learning signal or nonsense.","status":"live","lessonCount":4,"stepCount":28,"liveLessonCount":4,"liveStepCount":28,"estMinutes":28,"xpTotal":104},{"number":37,"slug":"dataset-pipelines","title":"dataset formats, ingestion, and validation pipelines","blurb":"a dataset is a product surface. build ingestion, validation, partitions, manifests, and checkpoints so the next run is not a mystery.","status":"live","lessonCount":5,"stepCount":35,"liveLessonCount":5,"liveStepCount":35,"estMinutes":37,"xpTotal":130},{"number":38,"slug":"ml-math-and-stats","title":"ml math and statistics that actually show up","blurb":"vectors, probability, distributions, correlation, and uncertainty are not trivia. they are how you read model behavior without worshipping it.","status":"live","lessonCount":5,"stepCount":35,"liveLessonCount":5,"liveStepCount":35,"estMinutes":37,"xpTotal":130},{"number":39,"slug":"supervised-learning-workflows","title":"supervised learning workflows","blurb":"labels, splits, baselines, training, prediction, and evaluation. the supervised workflow is the first complete model loop.","status":"live","lessonCount":5,"stepCount":35,"liveLessonCount":5,"liveStepCount":35,"estMinutes":40,"xpTotal":130},{"number":40,"slug":"unsupervised-learning-and-embeddings","title":"unsupervised learning, embeddings, and recommenders","blurb":"not every useful model has labels. cluster, compare, retrieve, and recommend by turning examples into useful neighborhoods.","status":"live","lessonCount":4,"stepCount":28,"liveLessonCount":4,"liveStepCount":28,"estMinutes":32,"xpTotal":104},{"number":41,"slug":"metrics-and-error-analysis","title":"metrics, slices, and error analysis","blurb":"accuracy is a blunt instrument. learn confusion matrices, precision, recall, thresholds, slices, and failure notes so model quality has evidence.","status":"live","lessonCount":5,"stepCount":35,"liveLessonCount":5,"liveStepCount":35,"estMinutes":37,"xpTotal":130},{"number":42,"slug":"pytorch-tensors-and-autograd","title":"pytorch tensors and autograd","blurb":"read tensor code without flinching. tensors, shapes, broadcasting, gradients, and autograd are the grammar of modern deep learning scripts.","status":"live","lessonCount":4,"stepCount":28,"liveLessonCount":4,"liveStepCount":28,"estMinutes":30,"xpTotal":104},{"number":43,"slug":"training-loops-and-optimizers","title":"training loops, backprop, optimizers, and schedulers","blurb":"the training loop is where models change. learn loss, gradients, optimizer steps, schedules, checkpoints, and the bugs ai ships there.","status":"live","lessonCount":5,"stepCount":35,"liveLessonCount":5,"liveStepCount":35,"estMinutes":37,"xpTotal":130},{"number":44,"slug":"deep-learning-architectures","title":"cnns, transformers, and useful llm internals","blurb":"architecture literacy for builders: convolution, attention, tokens, decoding, kv cache, quantization, and what those choices do to cost and behavior.","status":"live","lessonCount":5,"stepCount":35,"liveLessonCount":5,"liveStepCount":35,"estMinutes":37,"xpTotal":130},{"number":45,"slug":"feature-experiments-registries","title":"feature pipelines, experiment tracking, and registries","blurb":"features, runs, configs, artifacts, and registries are how ml work becomes repeatable instead of a lucky notebook.","status":"live","lessonCount":5,"stepCount":35,"liveLessonCount":5,"liveStepCount":35,"estMinutes":37,"xpTotal":130},{"number":46,"slug":"model-serving-and-mlops","title":"model serving, ci/cd, and mlops","blurb":"serving a model means handling inputs, versions, routes, batch jobs, ci gates, rollback, and production failures deliberately.","status":"live","lessonCount":6,"stepCount":42,"liveLessonCount":6,"liveStepCount":42,"estMinutes":44,"xpTotal":156},{"number":47,"slug":"monitoring-cloud-portfolio","title":"monitoring, drift, cloud scale, and portfolio launch","blurb":"the last mile: logs, drift, alerts, retraining decisions, cloud cost, gpu constraints, architecture docs, demos, and role stories.","status":"live","lessonCount":6,"stepCount":42,"liveLessonCount":6,"liveStepCount":42,"estMinutes":44,"xpTotal":156},{"number":48,"slug":"graphic-design-studio","title":"graphic design studio — prompt, kit, and fifty on-brand assets","blurb":"how a working designer runs image models: prompts written like creative briefs, a brand bible that travels as structured data — with the design tokens that carry it onto screens — and the seeds, reference locks, and QA filters that make fifty generated assets look like one studio shipped them.","status":"live","lessonCount":3,"stepCount":27,"liveLessonCount":3,"liveStepCount":27,"estMinutes":73,"xpTotal":82},{"number":49,"slug":"campaign-studio","title":"campaign studio — one campaign, end to end, with the gate on","blurb":"brief to voice-locked copy variants to batch plan to calendar to the numbers pass. the whole campaign as data your scripts can check — and an approval gate nothing skips. built for the person who owns the send button.","status":"live","lessonCount":3,"stepCount":22,"liveLessonCount":3,"liveStepCount":22,"estMinutes":59,"xpTotal":69},{"number":50,"slug":"support-studio","title":"support studio — the reply drafter you can trust","blurb":"how a working support agent runs AI: a policy pack the drafter can't talk around, a banned-promises linter that holds every draft, golden eval sets that make each macro earn autonomy one intent at a time, and the escalation line where money, law, and anger stay human.","status":"live","lessonCount":3,"stepCount":23,"liveLessonCount":3,"liveStepCount":23,"estMinutes":61,"xpTotal":71},{"number":51,"slug":"copy-studio","title":"copy studio — voice from evidence, variants at scale, claims that clear","blurb":"a client's voice measured from their own published copy, variant batches that pass the voice gate or die with a named reason, and a claim check that blocks the ship button while any fact is unsourced. corrections-log culture, as code.","status":"live","lessonCount":3,"stepCount":24,"liveLessonCount":3,"liveStepCount":24,"estMinutes":66,"xpTotal":72},{"number":52,"slug":"analytics-studio","title":"analytics studio — messy export to defensible memo","blurb":"how a working analyst runs AI: a cleaning log that accounts for every dropped row, sample-first checks that catch the plausible-but-wrong aggregation, a memo where every number carries the address of the cell that made it, SR 11-7-style challenge against the AI's recommendation, and the rerun test — same data, same code, same memo, or it isn't done.","status":"live","lessonCount":3,"stepCount":22,"liveLessonCount":3,"liveStepCount":22,"estMinutes":61,"xpTotal":74},{"number":53,"slug":"delivery-studio","title":"delivery studio — direct the build without becoming the bottleneck","blurb":"how a working delivery lead runs AI builders: specs with acceptance checks written before the build, a review that runs the checks instead of admiring the demo, status roll-ups computed from acceptance records instead of standup vibes, the not-ready call made on evidence you can read out loud to a steering committee, and an hours-and-dollars receipt — before/after on a named function, finance's loaded rate, a named owner, the accepted thing that shipped — small enough to defend in a staff meeting.","status":"live","lessonCount":4,"stepCount":32,"liveLessonCount":4,"liveStepCount":32,"estMinutes":74,"xpTotal":96},{"number":54,"slug":"people-studio","title":"people studio — draft fast, decide human, prove everything","blurb":"how a working hr specialist runs AI: a data firewall that keeps employee records out of prompts by code instead of willpower, recruiting briefs where every claim cites a resume line, policy drafts that cannot publish without a named legal reviewer, and the adverse-action paper trail that survives a discrimination claim.","status":"live","lessonCount":3,"stepCount":24,"liveLessonCount":3,"liveStepCount":24,"estMinutes":56,"xpTotal":72},{"number":55,"slug":"ops-studio","title":"ops studio — tribal knowledge to running automation","blurb":"how a working ops lead gets the process out of one person's head and into automation that can be trusted: SOPs captured as versioned data with the invented steps hunted down, recurring checklists with an explicit auto-run vs named-approval line, exception queues instead of silent failures, a receipt against the export for every number in the weekly report, and a PII proxy that masks member identifiers before the model and restores them only for the named human who sends.","status":"live","lessonCount":4,"stepCount":32,"liveLessonCount":4,"liveStepCount":32,"estMinutes":80,"xpTotal":96},{"number":56,"slug":"legal-studio","title":"legal studio — the cite-check gate and the log that survives","blurb":"how a working lawyer runs AI: a citation-verification drill where every authority gets opened at the source (the fabricated ones always look right), clause extraction that's worthless without a pinpoint, privilege rules written as a routing table instead of remembered under deadline, and the review log you'd want in the record when opposing counsel moves for sanctions.","status":"live","lessonCount":3,"stepCount":22,"liveLessonCount":3,"liveStepCount":22,"estMinutes":60,"xpTotal":69},{"number":57,"slug":"agent-studio","title":"agent studio — ship one agent feature before you stand up","blurb":"one sitting, one agent feature, end to end: a tool schema that makes the dangerous call a validation error, a loop that meters its own spend, golden cases wired before the router works, a trace you debug from instead of vibes, and the ratchet that turns tonight's incident into tomorrow's eval. practice at production tempo.","status":"live","lessonCount":3,"stepCount":23,"liveLessonCount":3,"liveStepCount":23,"estMinutes":66,"xpTotal":73}]},"accessToc":{"chapters":[{"slug":"before-you-build","lessons":[{"slug":"from-worker-to-builder","steps":[{"id":"before-you-build/from-worker-to-builder/s01-01-intro"}]},{"slug":"upgrade-dull-artifacts-into-interactive-sites","steps":[{"id":"before-you-build/upgrade-dull-artifacts-into-interactive-sites/s01-01-intro"},{"id":"before-you-build/upgrade-dull-artifacts-into-interactive-sites/s02-02-build-brief"},{"id":"before-you-build/upgrade-dull-artifacts-into-interactive-sites/s03-03-your-artifact-brief"}]},{"slug":"why-building-matters-now","steps":[{"id":"before-you-build/why-building-matters-now/s01-01-intro"}]},{"slug":"the-builder-loop","steps":[{"id":"before-you-build/the-builder-loop/s01-01-intro"}]},{"slug":"your-first-builder-brief","steps":[{"id":"before-you-build/your-first-builder-brief/s01-01-intro"}]},{"slug":"what-the-ai-is-doing","steps":[{"id":"before-you-build/what-the-ai-is-doing/s01-01-intro"}]},{"slug":"build-your-first-reusable-tool","steps":[{"id":"before-you-build/build-your-first-reusable-tool/s01-01-intro"}]},{"slug":"from-prompt-to-project","steps":[{"id":"before-you-build/from-prompt-to-project/s01-01-intro"}]},{"slug":"why-code-appears-later","steps":[{"id":"before-you-build/why-code-appears-later/s01-01-intro"}]},{"slug":"use-it-again","steps":[{"id":"before-you-build/use-it-again/s01-01-intro"},{"id":"before-you-build/use-it-again/s02-02-which-fix-compounds"},{"id":"before-you-build/use-it-again/s03-03-save-version-two"}]}]},{"slug":"read-the-script","lessons":[{"slug":"names-and-values","steps":[{"id":"read-the-script/names-and-values/s01-01-intro"},{"id":"read-the-script/names-and-values/s02-02-spot-the-type"},{"id":"read-the-script/names-and-values/s03-03-assignment"},{"id":"read-the-script/names-and-values/s04-04-predict-the-score"},{"id":"read-the-script/names-and-values/s05-05-fill-the-name"},{"id":"read-the-script/names-and-values/s06-06-fix-the-typo"},{"id":"read-the-script/names-and-values/s07-07-write-greeting"},{"id":"read-the-script/names-and-values/s08-08-checkpoint"}]},{"slug":"functions-and-the-hallucinated-return","steps":[{"id":"read-the-script/functions-and-the-hallucinated-return/s01-01-intro"},{"id":"read-the-script/functions-and-the-hallucinated-return/s02-02-which-returns"},{"id":"read-the-script/functions-and-the-hallucinated-return/s03-03-return-vs-print"},{"id":"read-the-script/functions-and-the-hallucinated-return/s04-04-predict-the-result"},{"id":"read-the-script/functions-and-the-hallucinated-return/s05-05-fix-the-missing-return"},{"id":"read-the-script/functions-and-the-hallucinated-return/s06-06-fix-print-vs-return"},{"id":"read-the-script/functions-and-the-hallucinated-return/s07-07-write-square"},{"id":"read-the-script/functions-and-the-hallucinated-return/s08-08-checkpoint"}]},{"slug":"decisions-if-elif","steps":[{"id":"read-the-script/decisions-if-elif/s01-01-intro"},{"id":"read-the-script/decisions-if-elif/s02-02-truthiness-quiz"},{"id":"read-the-script/decisions-if-elif/s03-03-eq-vs-is"},{"id":"read-the-script/decisions-if-elif/s04-04-predict-the-empty-list"},{"id":"read-the-script/decisions-if-elif/s05-05-fix-the-zero-bug"},{"id":"read-the-script/decisions-if-elif/s06-06-fix-the-elif-order"},{"id":"read-the-script/decisions-if-elif/s07-07-checkpoint"},{"id":"read-the-script/decisions-if-elif/s08-08-going-deeper"}]}]},{"slug":"read-the-data-shapes","lessons":[{"slug":"the-shapes-ai-dumps-on-you","steps":[{"id":"read-the-data-shapes/the-shapes-ai-dumps-on-you/s01-01-intro"},{"id":"read-the-data-shapes/the-shapes-ai-dumps-on-you/s02-02-which-is-which"},{"id":"read-the-data-shapes/the-shapes-ai-dumps-on-you/s03-03-nested-paths"},{"id":"read-the-data-shapes/the-shapes-ai-dumps-on-you/s04-04-predict-the-deep-key"},{"id":"read-the-data-shapes/the-shapes-ai-dumps-on-you/s05-05-fill-the-index"},{"id":"read-the-data-shapes/the-shapes-ai-dumps-on-you/s06-06-fix-the-keyerror"},{"id":"read-the-data-shapes/the-shapes-ai-dumps-on-you/s07-07-fix-the-list-vs-dict"},{"id":"read-the-data-shapes/the-shapes-ai-dumps-on-you/s08-08-checkpoint"}]},{"slug":"walking-the-shape","steps":[{"id":"read-the-data-shapes/walking-the-shape/s01-01-intro"},{"id":"read-the-data-shapes/walking-the-shape/s02-02-which-loop-shape"},{"id":"read-the-data-shapes/walking-the-shape/s03-03-walking-the-shape"},{"id":"read-the-data-shapes/walking-the-shape/s04-04-predict-the-list-loop"},{"id":"read-the-data-shapes/walking-the-shape/s05-05-fill-the-loop-variable"},{"id":"read-the-data-shapes/walking-the-shape/s06-06-fix-the-dict-loop"},{"id":"read-the-data-shapes/walking-the-shape/s07-07-write-sum-loop"},{"id":"read-the-data-shapes/walking-the-shape/s08-08-checkpoint"}]},{"slug":"comprehensions-and-the-wrong-layer-bug","steps":[{"id":"read-the-data-shapes/comprehensions-and-the-wrong-layer-bug/s01-01-intro"},{"id":"read-the-data-shapes/comprehensions-and-the-wrong-layer-bug/s02-02-which-comp-shape"},{"id":"read-the-data-shapes/comprehensions-and-the-wrong-layer-bug/s03-03-with-filter"},{"id":"read-the-data-shapes/comprehensions-and-the-wrong-layer-bug/s04-04-predict-the-comp"},{"id":"read-the-data-shapes/comprehensions-and-the-wrong-layer-bug/s05-05-fix-the-wrong-layer"},{"id":"read-the-data-shapes/comprehensions-and-the-wrong-layer-bug/s06-06-write-comp"},{"id":"read-the-data-shapes/comprehensions-and-the-wrong-layer-bug/s07-07-checkpoint"},{"id":"read-the-data-shapes/comprehensions-and-the-wrong-layer-bug/s08-08-going-deeper"}]}]},{"slug":"read-the-failure","lessons":[{"slug":"read-bottom-up","steps":[{"id":"read-the-failure/read-bottom-up/s01-01-anatomy"},{"id":"read-the-failure/read-bottom-up/s02-02-which-error"},{"id":"read-the-failure/read-bottom-up/s03-03-the-five-fingerprints"},{"id":"read-the-failure/read-bottom-up/s04-04-predict-the-class"},{"id":"read-the-failure/read-bottom-up/s05-05-fix-nameerror"},{"id":"read-the-failure/read-bottom-up/s06-06-fix-attributeerror"},{"id":"read-the-failure/read-bottom-up/s07-07-write-defensive"},{"id":"read-the-failure/read-bottom-up/s08-08-checkpoint"}]},{"slug":"try-except-what-ai-misuses","steps":[{"id":"read-the-failure/try-except-what-ai-misuses/s01-01-intro"},{"id":"read-the-failure/try-except-what-ai-misuses/s02-02-which-block-runs"},{"id":"read-the-failure/try-except-what-ai-misuses/s03-03-naming-the-error"},{"id":"read-the-failure/try-except-what-ai-misuses/s04-04-predict-the-branch"},{"id":"read-the-failure/try-except-what-ai-misuses/s05-05-fill-the-keyword"},{"id":"read-the-failure/try-except-what-ai-misuses/s06-06-fix-the-bare-except"},{"id":"read-the-failure/try-except-what-ai-misuses/s07-07-write-safe-lookup"},{"id":"read-the-failure/try-except-what-ai-misuses/s08-08-checkpoint"}]},{"slug":"fail-loudly","steps":[{"id":"read-the-failure/fail-loudly/s01-01-intro"},{"id":"read-the-failure/fail-loudly/s02-02-which-raise-fires"},{"id":"read-the-failure/fail-loudly/s03-03-predict-the-raise"},{"id":"read-the-failure/fail-loudly/s04-04-fill-the-raise-keyword"},{"id":"read-the-failure/fail-loudly/s05-05-fix-the-silent-swallow"},{"id":"read-the-failure/fail-loudly/s06-06-write-validate-age"},{"id":"read-the-failure/fail-loudly/s07-07-checkpoint"},{"id":"read-the-failure/fail-loudly/s08-08-going-deeper"}]}]},{"slug":"read-the-pipeline","lessons":[{"slug":"files-without-fear","steps":[{"id":"read-the-pipeline/files-without-fear/s01-01-intro"},{"id":"read-the-pipeline/files-without-fear/s02-02-which-mode"},{"id":"read-the-pipeline/files-without-fear/s03-03-pathlib-and-manifests"},{"id":"read-the-pipeline/files-without-fear/s04-04-predict-the-suffix"},{"id":"read-the-pipeline/files-without-fear/s05-05-fill-the-mode"},{"id":"read-the-pipeline/files-without-fear/s06-06-fix-the-wrong-mode"},{"id":"read-the-pipeline/files-without-fear/s07-07-write-manifest-entry"},{"id":"read-the-pipeline/files-without-fear/s08-08-checkpoint"}]},{"slug":"talking-to-apis","steps":[{"id":"read-the-pipeline/talking-to-apis/s01-01-intro"},{"id":"read-the-pipeline/talking-to-apis/s02-02-which-status-family"},{"id":"read-the-pipeline/talking-to-apis/s03-03-parsing-the-json"},{"id":"read-the-pipeline/talking-to-apis/s04-04-predict-the-key"},{"id":"read-the-pipeline/talking-to-apis/s05-05-fill-the-method"},{"id":"read-the-pipeline/talking-to-apis/s06-06-fix-the-status-check"},{"id":"read-the-pipeline/talking-to-apis/s07-07-write-classify-status"},{"id":"read-the-pipeline/talking-to-apis/s08-08-checkpoint"}]},{"slug":"when-the-pipeline-breaks","steps":[{"id":"read-the-pipeline/when-the-pipeline-breaks/s01-01-intro"},{"id":"read-the-pipeline/when-the-pipeline-breaks/s02-02-honor-the-retry-after"},{"id":"read-the-pipeline/when-the-pipeline-breaks/s03-03-predict-the-status-handling"},{"id":"read-the-pipeline/when-the-pipeline-breaks/s04-04-fill-the-raise-for-status"},{"id":"read-the-pipeline/when-the-pipeline-breaks/s05-05-fix-the-missing-check"},{"id":"read-the-pipeline/when-the-pipeline-breaks/s06-06-fix-the-broad-retry"},{"id":"read-the-pipeline/when-the-pipeline-breaks/s07-07-checkpoint"},{"id":"read-the-pipeline/when-the-pipeline-breaks/s08-08-going-deeper"}]}]},{"slug":"mutation-and-state","lessons":[{"slug":"why-it-breaks","steps":[{"id":"mutation-and-state/why-it-breaks/s01-01-intro"},{"id":"mutation-and-state/why-it-breaks/s02-02-which-mutates"},{"id":"mutation-and-state/why-it-breaks/s03-03-shared-reference"},{"id":"mutation-and-state/why-it-breaks/s04-04-fix-the-shared-list"},{"id":"mutation-and-state/why-it-breaks/s05-05-checkpoint"}]},{"slug":"copy-vs-reference","steps":[{"id":"mutation-and-state/copy-vs-reference/s01-01-deep-copy"},{"id":"mutation-and-state/copy-vs-reference/s02-02-predict-the-shallow"},{"id":"mutation-and-state/copy-vs-reference/s03-03-fix-the-shallow-bug"},{"id":"mutation-and-state/copy-vs-reference/s04-04-checkpoint"}]}]},{"slug":"llm-apis","lessons":[{"slug":"before-the-api-what-the-model-is-doing","steps":[{"id":"llm-apis/before-the-api-what-the-model-is-doing/s01-01-intro"}]},{"slug":"the-messages-pattern","steps":[{"id":"llm-apis/the-messages-pattern/s01-01-intro"},{"id":"llm-apis/the-messages-pattern/s02-02-which-role-is-yours"},{"id":"llm-apis/the-messages-pattern/s03-03-reading-the-response"},{"id":"llm-apis/the-messages-pattern/s04-04-predict-the-text"},{"id":"llm-apis/the-messages-pattern/s05-05-fill-the-role"},{"id":"llm-apis/the-messages-pattern/s06-06-fix-the-message-shape"},{"id":"llm-apis/the-messages-pattern/s07-07-fix-the-response-access"},{"id":"llm-apis/the-messages-pattern/s08-08-write-ask-claude"},{"id":"llm-apis/the-messages-pattern/s09-09-checkpoint"}]},{"slug":"reading-the-response","steps":[{"id":"llm-apis/reading-the-response/s01-01-intro"},{"id":"llm-apis/reading-the-response/s02-02-which-block-do-you-read"},{"id":"llm-apis/reading-the-response/s03-03-the-five-stop-reasons"},{"id":"llm-apis/reading-the-response/s04-04-predict-the-text"},{"id":"llm-apis/reading-the-response/s05-05-fill-the-text-extract"},{"id":"llm-apis/reading-the-response/s06-06-fix-the-content-zero"},{"id":"llm-apis/reading-the-response/s07-07-fix-the-stop-assumption"},{"id":"llm-apis/reading-the-response/s08-08-write-the-extractor"},{"id":"llm-apis/reading-the-response/s09-09-checkpoint"}]},{"slug":"the-model-picker","steps":[{"id":"llm-apis/the-model-picker/s01-01-why-model-choice-is-a-product-decision"},{"id":"llm-apis/the-model-picker/s02-02-haiku-territory"},{"id":"llm-apis/the-model-picker/s03-03-which-model-here"},{"id":"llm-apis/the-model-picker/s04-04-sonnet-territory"},{"id":"llm-apis/the-model-picker/s05-05-opus-and-the-thinking-budget"},{"id":"llm-apis/the-model-picker/s06-06-pick-the-model"},{"id":"llm-apis/the-model-picker/s07-07-write-the-model-routing-memo"},{"id":"llm-apis/the-model-picker/s08-08-checkpoint"}]}]},{"slug":"structured-output","lessons":[{"slug":"getting-json-back","steps":[{"id":"structured-output/getting-json-back/s01-01-intro"},{"id":"structured-output/getting-json-back/s02-02-why-validate"},{"id":"structured-output/getting-json-back/s03-03-pydantic-models"},{"id":"structured-output/getting-json-back/s04-04-predict-the-validated"},{"id":"structured-output/getting-json-back/s05-05-fill-the-field-type"},{"id":"structured-output/getting-json-back/s06-06-fix-the-required-field"},{"id":"structured-output/getting-json-back/s07-07-fix-the-type-mismatch"},{"id":"structured-output/getting-json-back/s08-08-write-parse-extraction"},{"id":"structured-output/getting-json-back/s09-09-checkpoint"}]},{"slug":"schemas-eat-prompts","steps":[{"id":"structured-output/schemas-eat-prompts/s01-01-the-trust-boundary"},{"id":"structured-output/schemas-eat-prompts/s02-02-three-shipped-breakages"},{"id":"structured-output/schemas-eat-prompts/s03-03-which-boundary-broke"},{"id":"structured-output/schemas-eat-prompts/s04-04-schema-as-prompt-replacement"},{"id":"structured-output/schemas-eat-prompts/s05-05-where-validation-belongs"},{"id":"structured-output/schemas-eat-prompts/s06-06-the-pydantic-migration-as-war-story"},{"id":"structured-output/schemas-eat-prompts/s07-07-write-the-boundary-audit"},{"id":"structured-output/schemas-eat-prompts/s08-08-checkpoint"}]},{"slug":"dataset-schema-validation","steps":[{"id":"structured-output/dataset-schema-validation/s01-01-validate-at-the-boundary"},{"id":"structured-output/dataset-schema-validation/s02-02-the-silent-drop"},{"id":"structured-output/dataset-schema-validation/s03-03-predict-the-missing-fields"},{"id":"structured-output/dataset-schema-validation/s04-04-fill-the-membership-test"},{"id":"structured-output/dataset-schema-validation/s05-05-fix-the-range-check"},{"id":"structured-output/dataset-schema-validation/s06-06-write-validate-batch"},{"id":"structured-output/dataset-schema-validation/s07-07-claims-with-receipts"},{"id":"structured-output/dataset-schema-validation/s08-08-checkpoint"}]}]},{"slug":"mcp","lessons":[{"slug":"what-mcp-is","steps":[{"id":"mcp/what-mcp-is/s01-01-intro"},{"id":"mcp/what-mcp-is/s02-02-which-side-is-the-server"},{"id":"mcp/what-mcp-is/s03-03-the-tool-list"},{"id":"mcp/what-mcp-is/s04-04-predict-the-tool-result"},{"id":"mcp/what-mcp-is/s05-05-fill-the-tool-name"},{"id":"mcp/what-mcp-is/s06-06-fix-the-missing-argument"},{"id":"mcp/what-mcp-is/s07-07-fix-the-result-shape"},{"id":"mcp/what-mcp-is/s08-08-write-call-tool"},{"id":"mcp/what-mcp-is/s09-09-checkpoint"}]},{"slug":"writing-a-tiny-mcp-server","steps":[{"id":"mcp/writing-a-tiny-mcp-server/s01-01-intro"},{"id":"mcp/writing-a-tiny-mcp-server/s02-02-which-message-is-call-tool"},{"id":"mcp/writing-a-tiny-mcp-server/s03-03-the-tool-registry"},{"id":"mcp/writing-a-tiny-mcp-server/s04-04-predict-the-list-tools-output"},{"id":"mcp/writing-a-tiny-mcp-server/s05-05-fill-the-input-schema"},{"id":"mcp/writing-a-tiny-mcp-server/s06-06-fix-the-missing-error-response"},{"id":"mcp/writing-a-tiny-mcp-server/s07-07-fix-the-validation-gap"},{"id":"mcp/writing-a-tiny-mcp-server/s08-08-write-the-call-tool-dispatcher"},{"id":"mcp/writing-a-tiny-mcp-server/s09-09-checkpoint"}]},{"slug":"why-mcp-won","steps":[{"id":"mcp/why-mcp-won/s01-01-the-graveyard-of-tool-protocols"},{"id":"mcp/why-mcp-won/s02-02-what-openai-plugins-got-wrong"},{"id":"mcp/why-mcp-won/s03-03-which-failure-mode"},{"id":"mcp/why-mcp-won/s04-04-the-mcp-bet"},{"id":"mcp/why-mcp-won/s05-05-the-network-effect"},{"id":"mcp/why-mcp-won/s06-06-spot-the-mcp-wedge"},{"id":"mcp/why-mcp-won/s07-07-write-the-protocol-postmortem"},{"id":"mcp/why-mcp-won/s08-08-checkpoint"}]}]},{"slug":"agent-loops","lessons":[{"slug":"the-loop","steps":[{"id":"agent-loops/the-loop/s01-01-intro"},{"id":"agent-loops/the-loop/s02-02-which-stop-reason"},{"id":"agent-loops/the-loop/s03-03-tool-result-shape"},{"id":"agent-loops/the-loop/s04-04-predict-the-next-call"},{"id":"agent-loops/the-loop/s05-05-fill-the-stop-condition"},{"id":"agent-loops/the-loop/s06-06-fix-the-tool-id"},{"id":"agent-loops/the-loop/s07-07-fix-the-loop-exit"},{"id":"agent-loops/the-loop/s08-08-write-the-loop"},{"id":"agent-loops/the-loop/s09-09-checkpoint"}]},{"slug":"multi-step-tools","steps":[{"id":"agent-loops/multi-step-tools/s01-01-intro"},{"id":"agent-loops/multi-step-tools/s02-02-which-tool-runs"},{"id":"agent-loops/multi-step-tools/s03-03-tool-registry"},{"id":"agent-loops/multi-step-tools/s04-04-predict-the-chain"},{"id":"agent-loops/multi-step-tools/s05-05-fill-the-dispatch"},{"id":"agent-loops/multi-step-tools/s06-06-fix-the-missing-tool"},{"id":"agent-loops/multi-step-tools/s07-07-fix-the-parallel-ids"},{"id":"agent-loops/multi-step-tools/s08-08-write-multi-tool-agent"},{"id":"agent-loops/multi-step-tools/s09-09-checkpoint"}]},{"slug":"routing","steps":[{"id":"agent-loops/routing/s01-01-intro"},{"id":"agent-loops/routing/s02-02-when-to-route"},{"id":"agent-loops/routing/s03-03-classifier-output"},{"id":"agent-loops/routing/s04-04-predict-the-route"},{"id":"agent-loops/routing/s05-05-fill-the-dispatch"},{"id":"agent-loops/routing/s06-06-fix-the-fallback"},{"id":"agent-loops/routing/s07-07-fix-the-loose-classifier"},{"id":"agent-loops/routing/s08-08-write-the-router"},{"id":"agent-loops/routing/s09-09-checkpoint"}]},{"slug":"evaluator-optimizer","steps":[{"id":"agent-loops/evaluator-optimizer/s01-01-intro"},{"id":"agent-loops/evaluator-optimizer/s02-02-when-it-earns-its-keep"},{"id":"agent-loops/evaluator-optimizer/s03-03-judge-output-shape"},{"id":"agent-loops/evaluator-optimizer/s04-04-predict-the-iterations"},{"id":"agent-loops/evaluator-optimizer/s05-05-fill-the-exit"},{"id":"agent-loops/evaluator-optimizer/s06-06-fix-the-judge-parsing"},{"id":"agent-loops/evaluator-optimizer/s07-07-fix-the-missing-cap"},{"id":"agent-loops/evaluator-optimizer/s08-08-write-the-evaluator-optimizer"},{"id":"agent-loops/evaluator-optimizer/s09-09-checkpoint"}]},{"slug":"why-every-framework-is-thirty-lines","steps":[{"id":"agent-loops/why-every-framework-is-thirty-lines/s01-01-the-frameworks-converged"},{"id":"agent-loops/why-every-framework-is-thirty-lines/s02-02-langgraph-walkthrough"},{"id":"agent-loops/why-every-framework-is-thirty-lines/s03-03-the-work-is-a-graph"},{"id":"agent-loops/why-every-framework-is-thirty-lines/s04-04-which-framework-fits"},{"id":"agent-loops/why-every-framework-is-thirty-lines/s05-05-vercel-ai-sdk-walkthrough"},{"id":"agent-loops/why-every-framework-is-thirty-lines/s06-06-the-five-canonical-patterns"},{"id":"agent-loops/why-every-framework-is-thirty-lines/s07-07-when-to-stay-framework-free"},{"id":"agent-loops/why-every-framework-is-thirty-lines/s08-08-write-the-tradeoff-memo"},{"id":"agent-loops/why-every-framework-is-thirty-lines/s09-09-checkpoint"}]},{"slug":"the-industry-map","steps":[{"id":"agent-loops/the-industry-map/s01-01-the-five-layers"},{"id":"agent-loops/the-industry-map/s02-02-which-layer-failed"},{"id":"agent-loops/the-industry-map/s03-03-the-shape-of-the-stack"}]}]},{"slug":"git-and-github","lessons":[{"slug":"the-three-states","steps":[{"id":"git-and-github/the-three-states/s01-01-intro"},{"id":"git-and-github/the-three-states/s02-02-which-command-stages"},{"id":"git-and-github/the-three-states/s03-03-status-and-diff"},{"id":"git-and-github/the-three-states/s04-04-predict-the-status"},{"id":"git-and-github/the-three-states/s05-05-fill-the-command"},{"id":"git-and-github/the-three-states/s06-06-fix-the-staged-files"},{"id":"git-and-github/the-three-states/s07-07-fix-the-pr-command"},{"id":"git-and-github/the-three-states/s08-08-write-status-summary"},{"id":"git-and-github/the-three-states/s09-09-checkpoint"}]},{"slug":"three-git-disasters-ai-shipped","steps":[{"id":"git-and-github/three-git-disasters-ai-shipped/s01-01-why-postmortems-teach-better"},{"id":"git-and-github/three-git-disasters-ai-shipped/s02-02-uber-2016-credentials-in-repo"},{"id":"git-and-github/three-git-disasters-ai-shipped/s03-03-which-control-would-have-caught-it"},{"id":"git-and-github/three-git-disasters-ai-shipped/s04-04-the-samsung-paste"},{"id":"git-and-github/three-git-disasters-ai-shipped/s05-05-the-cursor-git-add-dot-default"},{"id":"git-and-github/three-git-disasters-ai-shipped/s06-06-spot-the-failure-mode"},{"id":"git-and-github/three-git-disasters-ai-shipped/s07-07-write-your-pre-commit-checklist"},{"id":"git-and-github/three-git-disasters-ai-shipped/s08-08-checkpoint"}]},{"slug":"github-actions-for-model-checks","steps":[{"id":"git-and-github/github-actions-for-model-checks/s01-01-intro"},{"id":"git-and-github/github-actions-for-model-checks/s02-02-green-but-wrong"},{"id":"git-and-github/github-actions-for-model-checks/s03-03-predict-the-run"},{"id":"git-and-github/github-actions-for-model-checks/s04-04-fill-the-trigger"},{"id":"git-and-github/github-actions-for-model-checks/s05-05-fix-the-eval-gate"},{"id":"git-and-github/github-actions-for-model-checks/s06-06-write-run-job"},{"id":"git-and-github/github-actions-for-model-checks/s07-07-checkpoint"}]}]},{"slug":"secrets-and-env","lessons":[{"slug":"keeping-keys-safe","steps":[{"id":"secrets-and-env/keeping-keys-safe/s01-01-intro"},{"id":"secrets-and-env/keeping-keys-safe/s02-02-which-line-leaks"},{"id":"secrets-and-env/keeping-keys-safe/s03-03-loading-env-vars"},{"id":"secrets-and-env/keeping-keys-safe/s04-04-predict-the-key"},{"id":"secrets-and-env/keeping-keys-safe/s05-05-fill-the-getenv"},{"id":"secrets-and-env/keeping-keys-safe/s06-06-fix-the-hardcoded-key"},{"id":"secrets-and-env/keeping-keys-safe/s07-07-fix-the-missing-default"},{"id":"secrets-and-env/keeping-keys-safe/s08-08-write-load-config"},{"id":"secrets-and-env/keeping-keys-safe/s09-09-checkpoint"}]},{"slug":"ml-service-secrets","steps":[{"id":"secrets-and-env/ml-service-secrets/s01-01-intro"},{"id":"secrets-and-env/ml-service-secrets/s02-02-which-log-line-leaks"},{"id":"secrets-and-env/ml-service-secrets/s03-03-predict-the-scan"},{"id":"secrets-and-env/ml-service-secrets/s04-04-fill-the-lookup"},{"id":"secrets-and-env/ml-service-secrets/s05-05-fix-the-logged-key"},{"id":"secrets-and-env/ml-service-secrets/s06-06-write-scan-logs"},{"id":"secrets-and-env/ml-service-secrets/s07-07-checkpoint"}]}]},{"slug":"prompting","lessons":[{"slug":"builder-briefs-before-prompts","steps":[{"id":"prompting/builder-briefs-before-prompts/s01-01-intro"}]},{"slug":"the-prompt-craft","steps":[{"id":"prompting/the-prompt-craft/s01-01-intro"},{"id":"prompting/the-prompt-craft/s02-02-which-prompt-is-better"},{"id":"prompting/the-prompt-craft/s03-03-context-rot"},{"id":"prompting/the-prompt-craft/s04-04-predict-the-output"},{"id":"prompting/the-prompt-craft/s05-05-fill-the-constraint"},{"id":"prompting/the-prompt-craft/s06-06-fix-the-vague-prompt"},{"id":"prompting/the-prompt-craft/s07-07-fix-the-bloated-context"},{"id":"prompting/the-prompt-craft/s08-08-write-the-prompt"},{"id":"prompting/the-prompt-craft/s09-09-checkpoint"}]},{"slug":"few-shot-and-reasoning","steps":[{"id":"prompting/few-shot-and-reasoning/s01-01-intro"},{"id":"prompting/few-shot-and-reasoning/s02-02-when-few-shot-helps"},{"id":"prompting/few-shot-and-reasoning/s03-03-the-cot-trap"},{"id":"prompting/few-shot-and-reasoning/s04-04-predict-the-format-lock"},{"id":"prompting/few-shot-and-reasoning/s05-05-fill-the-example-format"},{"id":"prompting/few-shot-and-reasoning/s06-06-fix-the-cot-on-reasoning"},{"id":"prompting/few-shot-and-reasoning/s07-07-fix-the-format-mismatch"},{"id":"prompting/few-shot-and-reasoning/s08-08-write-the-prompt-builder"},{"id":"prompting/few-shot-and-reasoning/s09-09-checkpoint"}]},{"slug":"agent-config-files","steps":[{"id":"prompting/agent-config-files/s01-01-intro"},{"id":"prompting/agent-config-files/s02-02-which-belongs-in-the-file"},{"id":"prompting/agent-config-files/s03-03-anatomy-of-a-good-file"},{"id":"prompting/agent-config-files/s04-04-predict-which-rule-fires"},{"id":"prompting/agent-config-files/s05-05-fill-the-rule-block"},{"id":"prompting/agent-config-files/s06-06-fix-the-too-vague"},{"id":"prompting/agent-config-files/s07-07-fix-the-stale-pointer"},{"id":"prompting/agent-config-files/s08-08-write-a-claude-md"},{"id":"prompting/agent-config-files/s09-09-checkpoint"}]},{"slug":"what-aged-in-prompting","steps":[{"id":"prompting/what-aged-in-prompting/s01-01-prompting-as-a-moving-target"},{"id":"prompting/what-aged-in-prompting/s02-02-cot-then-vs-now"},{"id":"prompting/what-aged-in-prompting/s03-03-which-still-works"},{"id":"prompting/what-aged-in-prompting/s04-04-the-system-prompt-arms-race"},{"id":"prompting/what-aged-in-prompting/s05-05-spot-the-stale-technique"},{"id":"prompting/what-aged-in-prompting/s06-06-the-prompt-engineer-debate"},{"id":"prompting/what-aged-in-prompting/s07-07-write-the-cheatsheet-update"},{"id":"prompting/what-aged-in-prompting/s08-08-checkpoint"}]}]},{"slug":"agent-traces","lessons":[{"slug":"reading-the-trace","steps":[{"id":"agent-traces/reading-the-trace/s01-01-intro"},{"id":"agent-traces/reading-the-trace/s02-02-which-turn-failed"},{"id":"agent-traces/reading-the-trace/s03-03-the-stop-reasons"},{"id":"agent-traces/reading-the-trace/s04-04-predict-the-stop"},{"id":"agent-traces/reading-the-trace/s05-05-fill-the-tool-name"},{"id":"agent-traces/reading-the-trace/s06-06-fix-the-loop"},{"id":"agent-traces/reading-the-trace/s07-07-fix-the-arg-shape"},{"id":"agent-traces/reading-the-trace/s08-08-write-the-summarizer"},{"id":"agent-traces/reading-the-trace/s09-09-checkpoint"}]},{"slug":"trace-driven-debugging","steps":[{"id":"agent-traces/trace-driven-debugging/s01-01-intro"},{"id":"agent-traces/trace-driven-debugging/s02-02-which-pattern-is-this"},{"id":"agent-traces/trace-driven-debugging/s03-03-the-loop-signature"},{"id":"agent-traces/trace-driven-debugging/s04-04-predict-the-call-count"},{"id":"agent-traces/trace-driven-debugging/s05-05-fill-the-detector"},{"id":"agent-traces/trace-driven-debugging/s06-06-fix-the-tool-routing"},{"id":"agent-traces/trace-driven-debugging/s07-07-fix-the-prompt-bloat"},{"id":"agent-traces/trace-driven-debugging/s08-08-write-the-trace-summary"},{"id":"agent-traces/trace-driven-debugging/s09-09-checkpoint"}]},{"slug":"prediction-ids-and-inference-logs","steps":[{"id":"agent-traces/prediction-ids-and-inference-logs/s01-01-intro"},{"id":"agent-traces/prediction-ids-and-inference-logs/s02-02-pick-the-log-line"},{"id":"agent-traces/prediction-ids-and-inference-logs/s03-03-predict-the-ids"},{"id":"agent-traces/prediction-ids-and-inference-logs/s04-04-fill-the-join-key"},{"id":"agent-traces/prediction-ids-and-inference-logs/s05-05-fix-the-join"},{"id":"agent-traces/prediction-ids-and-inference-logs/s06-06-write-the-logger"},{"id":"agent-traces/prediction-ids-and-inference-logs/s07-07-checkpoint"}]}]},{"slug":"evals","lessons":[{"slug":"check-before-you-trust","steps":[{"id":"evals/check-before-you-trust/s01-01-intro"}]},{"slug":"writing-evals","steps":[{"id":"evals/writing-evals/s01-01-intro"},{"id":"evals/writing-evals/s02-02-which-eval-passes"},{"id":"evals/writing-evals/s03-03-eval-patterns"},{"id":"evals/writing-evals/s04-04-predict-the-pass-rate"},{"id":"evals/writing-evals/s05-05-fill-the-assertion"},{"id":"evals/writing-evals/s06-06-fix-the-flaky-eval"},{"id":"evals/writing-evals/s07-07-fix-the-overstrict-eval"},{"id":"evals/writing-evals/s08-08-write-the-suite"},{"id":"evals/writing-evals/s09-09-checkpoint"}]},{"slug":"llm-as-judge","steps":[{"id":"evals/llm-as-judge/s01-01-intro"},{"id":"evals/llm-as-judge/s02-02-pairwise-or-rubric"},{"id":"evals/llm-as-judge/s03-03-the-four-biases"},{"id":"evals/llm-as-judge/s04-04-predict-the-bias"},{"id":"evals/llm-as-judge/s05-05-fill-the-rubric-call"},{"id":"evals/llm-as-judge/s06-06-fix-the-likert-trap"},{"id":"evals/llm-as-judge/s07-07-fix-the-position-bias"},{"id":"evals/llm-as-judge/s08-08-write-the-rubric-judge"},{"id":"evals/llm-as-judge/s09-09-checkpoint"}]},{"slug":"the-rise-of-evals-as-a-discipline","steps":[{"id":"evals/the-rise-of-evals-as-a-discipline/s01-01-the-prompt-engineering-era"},{"id":"evals/the-rise-of-evals-as-a-discipline/s02-02-the-eval-turn"},{"id":"evals/the-rise-of-evals-as-a-discipline/s03-03-which-company-survives-a-model-swap"},{"id":"evals/the-rise-of-evals-as-a-discipline/s04-04-case-studies"},{"id":"evals/the-rise-of-evals-as-a-discipline/s05-05-eval-first-vs-prompt-first"},{"id":"evals/the-rise-of-evals-as-a-discipline/s06-06-why-the-eval-engineer-eats-the-prompt-engineer"},{"id":"evals/the-rise-of-evals-as-a-discipline/s07-07-write-the-eval-readiness-audit"},{"id":"evals/the-rise-of-evals-as-a-discipline/s08-08-checkpoint"}]},{"slug":"model-validation-gates","steps":[{"id":"evals/model-validation-gates/s01-01-intro"},{"id":"evals/model-validation-gates/s02-02-spot-the-theater"},{"id":"evals/model-validation-gates/s03-03-predict-the-decision"},{"id":"evals/model-validation-gates/s04-04-fill-the-regression-check"},{"id":"evals/model-validation-gates/s05-05-fix-the-theater-gate"},{"id":"evals/model-validation-gates/s06-06-write-the-gate-runner"},{"id":"evals/model-validation-gates/s07-07-checkpoint"}]}]},{"slug":"context-and-retrieval","lessons":[{"slug":"chunking-that-respects-structure","steps":[{"id":"context-and-retrieval/chunking-that-respects-structure/s01-01-intro"},{"id":"context-and-retrieval/chunking-that-respects-structure/s02-02-which-content-shape-breaks"},{"id":"context-and-retrieval/chunking-that-respects-structure/s03-03-the-recursive-splitter"},{"id":"context-and-retrieval/chunking-that-respects-structure/s04-04-predict-the-shred"},{"id":"context-and-retrieval/chunking-that-respects-structure/s05-05-fill-the-separator-list"},{"id":"context-and-retrieval/chunking-that-respects-structure/s06-06-fix-the-mid-sentence-cut"},{"id":"context-and-retrieval/chunking-that-respects-structure/s07-07-fix-the-missing-overlap"},{"id":"context-and-retrieval/chunking-that-respects-structure/s08-08-write-the-recursive-splitter"},{"id":"context-and-retrieval/chunking-that-respects-structure/s09-09-checkpoint"}]},{"slug":"embedding-that-fits-the-budget","steps":[{"id":"context-and-retrieval/embedding-that-fits-the-budget/s01-01-intro"},{"id":"context-and-retrieval/embedding-that-fits-the-budget/s02-02-which-model-fits"},{"id":"context-and-retrieval/embedding-that-fits-the-budget/s03-03-the-vector-space"},{"id":"context-and-retrieval/embedding-that-fits-the-budget/s04-04-predict-the-closest"},{"id":"context-and-retrieval/embedding-that-fits-the-budget/s05-05-fill-the-cosine-formula"},{"id":"context-and-retrieval/embedding-that-fits-the-budget/s06-06-fix-the-wrong-embedding-model"},{"id":"context-and-retrieval/embedding-that-fits-the-budget/s07-07-fix-the-missing-normalization"},{"id":"context-and-retrieval/embedding-that-fits-the-budget/s08-08-write-the-similarity-ranker"},{"id":"context-and-retrieval/embedding-that-fits-the-budget/s09-09-checkpoint"}]},{"slug":"retrieval-that-finds-the-right-thing","steps":[{"id":"context-and-retrieval/retrieval-that-finds-the-right-thing/s01-01-intro"},{"id":"context-and-retrieval/retrieval-that-finds-the-right-thing/s02-02-which-result-is-good"},{"id":"context-and-retrieval/retrieval-that-finds-the-right-thing/s03-03-the-distance-threshold"},{"id":"context-and-retrieval/retrieval-that-finds-the-right-thing/s04-04-predict-the-top-k"},{"id":"context-and-retrieval/retrieval-that-finds-the-right-thing/s05-05-fill-the-cutoff"},{"id":"context-and-retrieval/retrieval-that-finds-the-right-thing/s06-06-fix-the-no-threshold"},{"id":"context-and-retrieval/retrieval-that-finds-the-right-thing/s07-07-fix-the-dup-results"},{"id":"context-and-retrieval/retrieval-that-finds-the-right-thing/s08-08-write-the-ranker"},{"id":"context-and-retrieval/retrieval-that-finds-the-right-thing/s09-09-checkpoint"}]},{"slug":"rag-vs-long-context-vs-fine-tune","steps":[{"id":"context-and-retrieval/rag-vs-long-context-vs-fine-tune/s01-01-the-three-way-fork"},{"id":"context-and-retrieval/rag-vs-long-context-vs-fine-tune/s02-02-rag-when-you-need-freshness"},{"id":"context-and-retrieval/rag-vs-long-context-vs-fine-tune/s03-03-which-fork-for-this-scenario"},{"id":"context-and-retrieval/rag-vs-long-context-vs-fine-tune/s04-04-long-context-when-the-corpus-fits"},{"id":"context-and-retrieval/rag-vs-long-context-vs-fine-tune/s05-05-fine-tune-when-style-or-format-is-the-product"},{"id":"context-and-retrieval/rag-vs-long-context-vs-fine-tune/s06-06-which-fork-dies-first"},{"id":"context-and-retrieval/rag-vs-long-context-vs-fine-tune/s07-07-graph-vector-or-both"},{"id":"context-and-retrieval/rag-vs-long-context-vs-fine-tune/s08-08-the-rubric"},{"id":"context-and-retrieval/rag-vs-long-context-vs-fine-tune/s09-09-write-the-fork-decision"},{"id":"context-and-retrieval/rag-vs-long-context-vs-fine-tune/s10-10-checkpoint"}]},{"slug":"retrieval-metrics-and-vector-db-shape","steps":[{"id":"context-and-retrieval/retrieval-metrics-and-vector-db-shape/s01-01-the-eval-set"},{"id":"context-and-retrieval/retrieval-metrics-and-vector-db-shape/s02-02-filter-or-search-first"},{"id":"context-and-retrieval/retrieval-metrics-and-vector-db-shape/s03-03-predict-recall-precision"},{"id":"context-and-retrieval/retrieval-metrics-and-vector-db-shape/s04-04-fill-the-reciprocal"},{"id":"context-and-retrieval/retrieval-metrics-and-vector-db-shape/s05-05-fix-the-late-filter"},{"id":"context-and-retrieval/retrieval-metrics-and-vector-db-shape/s06-06-write-recall-at-k"},{"id":"context-and-retrieval/retrieval-metrics-and-vector-db-shape/s07-07-checkpoint"}]}]},{"slug":"production-tradeoffs","lessons":[{"slug":"prompt-caching-correctly","steps":[{"id":"production-tradeoffs/prompt-caching-correctly/s01-01-intro"},{"id":"production-tradeoffs/prompt-caching-correctly/s02-02-which-piece-caches"},{"id":"production-tradeoffs/prompt-caching-correctly/s03-03-the-cache-breakpoints"},{"id":"production-tradeoffs/prompt-caching-correctly/s04-04-predict-the-savings"},{"id":"production-tradeoffs/prompt-caching-correctly/s05-05-fill-the-cache-control"},{"id":"production-tradeoffs/prompt-caching-correctly/s06-06-fix-the-cache-buster"},{"id":"production-tradeoffs/prompt-caching-correctly/s07-07-fix-the-ttl-default"},{"id":"production-tradeoffs/prompt-caching-correctly/s08-08-write-the-cost-estimator"},{"id":"production-tradeoffs/prompt-caching-correctly/s09-09-checkpoint"}]},{"slug":"read-the-token-bill","steps":[{"id":"production-tradeoffs/read-the-token-bill/s01-01-intro"},{"id":"production-tradeoffs/read-the-token-bill/s02-02-which-prompt-costs-more"},{"id":"production-tradeoffs/read-the-token-bill/s03-03-the-shape-of-a-bill"},{"id":"production-tradeoffs/read-the-token-bill/s04-04-predict-the-monthly-spend"},{"id":"production-tradeoffs/read-the-token-bill/s05-05-fill-the-cost-formula"},{"id":"production-tradeoffs/read-the-token-bill/s06-06-fix-the-pricing-ratio-error"},{"id":"production-tradeoffs/read-the-token-bill/s07-07-fix-the-units-error"},{"id":"production-tradeoffs/read-the-token-bill/s08-08-write-the-cost-estimator"},{"id":"production-tradeoffs/read-the-token-bill/s09-09-checkpoint"}]},{"slug":"the-model-price-war","steps":[{"id":"production-tradeoffs/the-model-price-war/s01-01-the-price-curve"},{"id":"production-tradeoffs/the-model-price-war/s02-02-three-bets-and-how-they-aged"},{"id":"production-tradeoffs/the-model-price-war/s03-03-which-startup-survived"},{"id":"production-tradeoffs/the-model-price-war/s04-04-the-incumbent-trap"},{"id":"production-tradeoffs/the-model-price-war/s05-05-features-now-viable"},{"id":"production-tradeoffs/the-model-price-war/s06-06-pricing-for-a-war-you-cant-predict"},{"id":"production-tradeoffs/the-model-price-war/s07-07-write-the-cost-model"},{"id":"production-tradeoffs/the-model-price-war/s08-08-checkpoint"}]},{"slug":"batch-realtime-costs","steps":[{"id":"production-tradeoffs/batch-realtime-costs/s01-01-who-is-waiting"},{"id":"production-tradeoffs/batch-realtime-costs/s02-02-which-lane"},{"id":"production-tradeoffs/batch-realtime-costs/s03-03-predict-the-bill"},{"id":"production-tradeoffs/batch-realtime-costs/s04-04-fill-the-miss-rate"},{"id":"production-tradeoffs/batch-realtime-costs/s05-05-fix-the-free-discount"},{"id":"production-tradeoffs/batch-realtime-costs/s06-06-write-monthly-bill"},{"id":"production-tradeoffs/batch-realtime-costs/s07-07-checkpoint"}]}]},{"slug":"debugging-output","lessons":[{"slug":"read-the-trace-not-the-chat","steps":[{"id":"debugging-output/read-the-trace-not-the-chat/s01-01-intro"},{"id":"debugging-output/read-the-trace-not-the-chat/s02-02-where-to-look-first"},{"id":"debugging-output/read-the-trace-not-the-chat/s03-03-the-four-failure-classes"},{"id":"debugging-output/read-the-trace-not-the-chat/s04-04-predict-the-bad-turn"},{"id":"debugging-output/read-the-trace-not-the-chat/s05-05-fill-the-find-bad-turn"},{"id":"debugging-output/read-the-trace-not-the-chat/s06-06-fix-the-fix-the-symptom"},{"id":"debugging-output/read-the-trace-not-the-chat/s07-07-fix-the-blame-the-model"},{"id":"debugging-output/read-the-trace-not-the-chat/s08-08-write-the-trace-summary"},{"id":"debugging-output/read-the-trace-not-the-chat/s09-09-checkpoint"}]},{"slug":"the-four-breakage-classes","steps":[{"id":"debugging-output/the-four-breakage-classes/s01-01-intro"},{"id":"debugging-output/the-four-breakage-classes/s02-02-classify-the-refund-bug"},{"id":"debugging-output/the-four-breakage-classes/s03-03-the-trace-anatomy"},{"id":"debugging-output/the-four-breakage-classes/s04-04-predict-the-class"},{"id":"debugging-output/the-four-breakage-classes/s05-05-fill-the-class-name"},{"id":"debugging-output/the-four-breakage-classes/s06-06-fix-the-misclassification"},{"id":"debugging-output/the-four-breakage-classes/s07-07-fix-the-parse-mangle"},{"id":"debugging-output/the-four-breakage-classes/s08-08-write-the-classifier"},{"id":"debugging-output/the-four-breakage-classes/s09-09-checkpoint"}]},{"slug":"five-real-postmortems","steps":[{"id":"debugging-output/five-real-postmortems/s01-01-the-postmortem-template"},{"id":"debugging-output/five-real-postmortems/s02-02-air-canada-refund-lawsuit"},{"id":"debugging-output/five-real-postmortems/s03-03-dpd-and-nyc-mycity"},{"id":"debugging-output/five-real-postmortems/s04-04-classify-the-five"},{"id":"debugging-output/five-real-postmortems/s05-05-recruiter-json-mangle"},{"id":"debugging-output/five-real-postmortems/s06-06-glean-style-retrieval-miss"},{"id":"debugging-output/five-real-postmortems/s07-07-which-fix-catches-the-most"},{"id":"debugging-output/five-real-postmortems/s08-08-write-the-postmortem"},{"id":"debugging-output/five-real-postmortems/s09-09-checkpoint"}]},{"slug":"prediction-failure-triage","steps":[{"id":"debugging-output/prediction-failure-triage/s01-01-reproduce-classify-route"},{"id":"debugging-output/prediction-failure-triage/s02-02-first-move"},{"id":"debugging-output/prediction-failure-triage/s03-03-predict-the-route"},{"id":"debugging-output/prediction-failure-triage/s04-04-fill-the-owners"},{"id":"debugging-output/prediction-failure-triage/s05-05-fix-the-paraphrase-repro"},{"id":"debugging-output/prediction-failure-triage/s06-06-write-the-router"},{"id":"debugging-output/prediction-failure-triage/s07-07-checkpoint"}]}]},{"slug":"capstone","lessons":[{"slug":"pick-a-project-that-ships","steps":[{"id":"capstone/pick-a-project-that-ships/s01-01-the-builders-graveyard"},{"id":"capstone/pick-a-project-that-ships/s02-02-which-project-survives-contact-with-reality"},{"id":"capstone/pick-a-project-that-ships/s03-03-the-three-shapes-that-ship"},{"id":"capstone/pick-a-project-that-ships/s04-04-the-wedge-checklist"},{"id":"capstone/pick-a-project-that-ships/s05-05-spot-the-missing-wedge"},{"id":"capstone/pick-a-project-that-ships/s06-06-scope-down-the-capstone"},{"id":"capstone/pick-a-project-that-ships/s07-07-checkpoint"}]},{"slug":"build-a-cli-agent","steps":[{"id":"capstone/build-a-cli-agent/s01-01-intro"},{"id":"capstone/build-a-cli-agent/s02-02-which-piece-is-missing"},{"id":"capstone/build-a-cli-agent/s03-03-the-tool-loop"},{"id":"capstone/build-a-cli-agent/s04-04-predict-the-final-answer"},{"id":"capstone/build-a-cli-agent/s05-05-fill-the-stop-check"},{"id":"capstone/build-a-cli-agent/s06-06-fix-the-tool-dispatch"},{"id":"capstone/build-a-cli-agent/s07-07-fix-the-message-append"},{"id":"capstone/build-a-cli-agent/s08-08-the-logging-pattern"},{"id":"capstone/build-a-cli-agent/s09-09-write-the-tool-runner"},{"id":"capstone/build-a-cli-agent/s10-10-fix-the-loop-exit"},{"id":"capstone/build-a-cli-agent/s11-11-write-the-agent"},{"id":"capstone/build-a-cli-agent/s12-12-checkpoint"}]},{"slug":"wire-the-real-model","steps":[{"id":"capstone/wire-the-real-model/s01-01-intro"},{"id":"capstone/wire-the-real-model/s02-02-where-the-key-lives"},{"id":"capstone/wire-the-real-model/s03-03-the-sdk-response-shape"},{"id":"capstone/wire-the-real-model/s04-04-predict-the-block-type"},{"id":"capstone/wire-the-real-model/s05-05-fill-the-key-load"},{"id":"capstone/wire-the-real-model/s06-06-fix-the-hardcoded-key"},{"id":"capstone/wire-the-real-model/s07-07-fix-the-block-access"},{"id":"capstone/wire-the-real-model/s08-08-write-the-shape-adapter"},{"id":"capstone/wire-the-real-model/s09-09-checkpoint"}]},{"slug":"validate-tool-inputs","steps":[{"id":"capstone/validate-tool-inputs/s01-01-intro"},{"id":"capstone/validate-tool-inputs/s02-02-which-input-needs-validation"},{"id":"capstone/validate-tool-inputs/s03-03-the-validator-surface"},{"id":"capstone/validate-tool-inputs/s04-04-predict-the-error"},{"id":"capstone/validate-tool-inputs/s05-05-fill-the-validate-call"},{"id":"capstone/validate-tool-inputs/s06-06-fix-the-untyped-tool"},{"id":"capstone/validate-tool-inputs/s07-07-fix-the-error-leak"},{"id":"capstone/validate-tool-inputs/s08-08-write-the-validator"},{"id":"capstone/validate-tool-inputs/s09-09-checkpoint"}]},{"slug":"add-evals-and-traces","steps":[{"id":"capstone/add-evals-and-traces/s01-01-intro"},{"id":"capstone/add-evals-and-traces/s02-02-which-eval-fits"},{"id":"capstone/add-evals-and-traces/s03-03-the-trace-shape"},{"id":"capstone/add-evals-and-traces/s04-04-predict-the-pass-rate"},{"id":"capstone/add-evals-and-traces/s05-05-fill-the-trace-append"},{"id":"capstone/add-evals-and-traces/s06-06-fix-the-trace-mutation"},{"id":"capstone/add-evals-and-traces/s07-07-fix-the-tautological-eval"},{"id":"capstone/add-evals-and-traces/s08-08-write-the-eval-runner"},{"id":"capstone/add-evals-and-traces/s09-09-checkpoint"}]},{"slug":"wire-an-mcp-tool","steps":[{"id":"capstone/wire-an-mcp-tool/s01-01-intro"},{"id":"capstone/wire-an-mcp-tool/s02-02-when-to-use-mcp"},{"id":"capstone/wire-an-mcp-tool/s03-03-the-mcp-protocol"},{"id":"capstone/wire-an-mcp-tool/s04-04-predict-the-tool-list"},{"id":"capstone/wire-an-mcp-tool/s05-05-fill-the-tools-call"},{"id":"capstone/wire-an-mcp-tool/s06-06-fix-the-result-shape"},{"id":"capstone/wire-an-mcp-tool/s07-07-fix-the-iserror-flag"},{"id":"capstone/wire-an-mcp-tool/s08-08-write-the-mcp-bridge"},{"id":"capstone/wire-an-mcp-tool/s09-09-checkpoint"}]},{"slug":"portfolio-ml-system-option","steps":[{"id":"capstone/portfolio-ml-system-option/s01-01-the-other-capstone"},{"id":"capstone/portfolio-ml-system-option/s02-02-what-reviewers-open"},{"id":"capstone/portfolio-ml-system-option/s03-03-predict-the-gate"},{"id":"capstone/portfolio-ml-system-option/s04-04-fill-the-gate"},{"id":"capstone/portfolio-ml-system-option/s05-05-fix-the-train-accuracy-gate"},{"id":"capstone/portfolio-ml-system-option/s06-06-write-the-scope-check"},{"id":"capstone/portfolio-ml-system-option/s07-07-checkpoint"}]}]},{"slug":"agent-harnesses","lessons":[{"slug":"project-workspaces-not-product-names","steps":[{"id":"agent-harnesses/project-workspaces-not-product-names/s01-01-intro"}]},{"slug":"what-a-harness-is","steps":[{"id":"agent-harnesses/what-a-harness-is/s01-01-intro"},{"id":"agent-harnesses/what-a-harness-is/s02-02-which-is-a-harness"},{"id":"agent-harnesses/what-a-harness-is/s03-03-the-four-layers"},{"id":"agent-harnesses/what-a-harness-is/s04-04-predict-the-layer"},{"id":"agent-harnesses/what-a-harness-is/s05-05-fill-the-dispatch"},{"id":"agent-harnesses/what-a-harness-is/s06-06-fix-the-no-retry"},{"id":"agent-harnesses/what-a-harness-is/s07-07-fix-the-hardcoded-registry"},{"id":"agent-harnesses/what-a-harness-is/s08-08-write-mini-harness"},{"id":"agent-harnesses/what-a-harness-is/s09-09-checkpoint"}]},{"slug":"architecting-an-ai-native-workflow","steps":[{"id":"agent-harnesses/architecting-an-ai-native-workflow/s01-01-intro"},{"id":"agent-harnesses/architecting-an-ai-native-workflow/s02-02-which-workflow-fits"},{"id":"agent-harnesses/architecting-an-ai-native-workflow/s03-03-mapping-the-workflow"},{"id":"agent-harnesses/architecting-an-ai-native-workflow/s04-04-predict-the-readiness-score"},{"id":"agent-harnesses/architecting-an-ai-native-workflow/s05-05-fill-the-required-fields"},{"id":"agent-harnesses/architecting-an-ai-native-workflow/s06-06-fix-the-implicit-policy"},{"id":"agent-harnesses/architecting-an-ai-native-workflow/s07-07-fix-the-wrong-metric"},{"id":"agent-harnesses/architecting-an-ai-native-workflow/s08-08-write-the-workflow-validator"},{"id":"agent-harnesses/architecting-an-ai-native-workflow/s09-09-checkpoint"}]},{"slug":"five-industries-walked-through","steps":[{"id":"agent-harnesses/five-industries-walked-through/s01-01-the-case-study-method"},{"id":"agent-harnesses/five-industries-walked-through/s02-02-home-services"},{"id":"agent-harnesses/five-industries-walked-through/s03-03-which-task-belongs-to-the-agent"},{"id":"agent-harnesses/five-industries-walked-through/s04-04-insurance-brokerage"},{"id":"agent-harnesses/five-industries-walked-through/s05-05-recruiting-firm"},{"id":"agent-harnesses/five-industries-walked-through/s06-06-which-industry-wedges-fastest"},{"id":"agent-harnesses/five-industries-walked-through/s07-07-the-incumbent-trap"},{"id":"agent-harnesses/five-industries-walked-through/s08-08-write-the-process-debt-audit"},{"id":"agent-harnesses/five-industries-walked-through/s09-09-checkpoint"}]},{"slug":"incident-runbook-from-the-repo","steps":[{"id":"agent-harnesses/incident-runbook-from-the-repo/s01-01-intro"},{"id":"agent-harnesses/incident-runbook-from-the-repo/s02-02-which-is-a-runbook"},{"id":"agent-harnesses/incident-runbook-from-the-repo/s03-03-detect-decide-writeback"},{"id":"agent-harnesses/incident-runbook-from-the-repo/s04-04-predict-the-decision"},{"id":"agent-harnesses/incident-runbook-from-the-repo/s05-05-fill-the-decision-rule"},{"id":"agent-harnesses/incident-runbook-from-the-repo/s06-06-fix-the-wiki-page"},{"id":"agent-harnesses/incident-runbook-from-the-repo/s07-07-fix-the-unnamed-human"},{"id":"agent-harnesses/incident-runbook-from-the-repo/s08-08-write-the-runbook"},{"id":"agent-harnesses/incident-runbook-from-the-repo/s09-09-checkpoint"}]}]},{"slug":"ai-image-generation","lessons":[{"slug":"the-image-model-landscape","steps":[{"id":"ai-image-generation/the-image-model-landscape/s01-01-the-six-families"},{"id":"ai-image-generation/the-image-model-landscape/s02-02-flux-vs-midjourney"},{"id":"ai-image-generation/the-image-model-landscape/s03-03-pick-the-model"},{"id":"ai-image-generation/the-image-model-landscape/s04-04-nano-banana-and-the-batch-economics"},{"id":"ai-image-generation/the-image-model-landscape/s05-05-text-in-image"},{"id":"ai-image-generation/the-image-model-landscape/s06-06-which-model-for-text"},{"id":"ai-image-generation/the-image-model-landscape/s07-07-the-decision-tree"},{"id":"ai-image-generation/the-image-model-landscape/s08-08-write-pick-image-model"},{"id":"ai-image-generation/the-image-model-landscape/s09-09-checkpoint"}]},{"slug":"prompting-for-real-output","steps":[{"id":"ai-image-generation/prompting-for-real-output/s01-01-why-the-girl-with-red-hair-fails"},{"id":"ai-image-generation/prompting-for-real-output/s02-02-the-eight-knobs"},{"id":"ai-image-generation/prompting-for-real-output/s03-03-fix-the-vague-prompt"},{"id":"ai-image-generation/prompting-for-real-output/s04-04-controlnet-and-reference"},{"id":"ai-image-generation/prompting-for-real-output/s05-05-which-knob-is-missing"},{"id":"ai-image-generation/prompting-for-real-output/s06-06-failure-modes"},{"id":"ai-image-generation/prompting-for-real-output/s07-07-write-score-image-prompt"},{"id":"ai-image-generation/prompting-for-real-output/s08-08-checkpoint"}]},{"slug":"the-image-pipeline","steps":[{"id":"ai-image-generation/the-image-pipeline/s01-01-the-six-stages"},{"id":"ai-image-generation/the-image-pipeline/s02-02-batch-and-filter"},{"id":"ai-image-generation/the-image-pipeline/s03-03-which-stage-is-broken"},{"id":"ai-image-generation/the-image-pipeline/s04-04-format-and-platform"},{"id":"ai-image-generation/the-image-pipeline/s05-05-fill-the-pipeline"},{"id":"ai-image-generation/the-image-pipeline/s06-06-write-cost-for-batch"},{"id":"ai-image-generation/the-image-pipeline/s07-07-checkpoint"}]}]},{"slug":"ai-video-generation","lessons":[{"slug":"the-video-model-lineup","steps":[{"id":"ai-video-generation/the-video-model-lineup/s01-01-the-landscape"},{"id":"ai-video-generation/the-video-model-lineup/s02-02-sora-and-veo"},{"id":"ai-video-generation/the-video-model-lineup/s03-03-higgsfield-and-camera-control"},{"id":"ai-video-generation/the-video-model-lineup/s04-04-the-second-wave"},{"id":"ai-video-generation/the-video-model-lineup/s05-05-text-vs-image-vs-video"},{"id":"ai-video-generation/the-video-model-lineup/s06-06-which-lane"},{"id":"ai-video-generation/the-video-model-lineup/s07-07-pick-the-model"},{"id":"ai-video-generation/the-video-model-lineup/s08-08-write-pick-video-model"},{"id":"ai-video-generation/the-video-model-lineup/s09-09-checkpoint"}]},{"slug":"camera-control-and-motion","steps":[{"id":"ai-video-generation/camera-control-and-motion/s01-01-the-static-camera-problem"},{"id":"ai-video-generation/camera-control-and-motion/s02-02-shot-vocabulary"},{"id":"ai-video-generation/camera-control-and-motion/s03-03-which-shot-is-which"},{"id":"ai-video-generation/camera-control-and-motion/s04-04-camera-moves"},{"id":"ai-video-generation/camera-control-and-motion/s05-05-the-i2v-keyframe-pattern"},{"id":"ai-video-generation/camera-control-and-motion/s06-06-spot-the-generic-prompt"},{"id":"ai-video-generation/camera-control-and-motion/s07-07-write-audit-shot-list"},{"id":"ai-video-generation/camera-control-and-motion/s08-08-checkpoint"}]},{"slug":"the-cost-math","steps":[{"id":"ai-video-generation/the-cost-math/s01-01-the-unit-economics"},{"id":"ai-video-generation/the-cost-math/s02-02-the-retake-rate-reality"},{"id":"ai-video-generation/the-cost-math/s03-03-which-tier-for-this-budget"},{"id":"ai-video-generation/the-cost-math/s04-04-the-60-second-promo"},{"id":"ai-video-generation/the-cost-math/s05-05-write-cost-per-minute"},{"id":"ai-video-generation/the-cost-math/s06-06-checkpoint"}]}]},{"slug":"programmatic-design","lessons":[{"slug":"why-programmatic","steps":[{"id":"programmatic-design/why-programmatic/s01-01-intro"},{"id":"programmatic-design/why-programmatic/s02-02-the-three-jobs"},{"id":"programmatic-design/why-programmatic/s03-03-which-task-is-code"},{"id":"programmatic-design/why-programmatic/s04-04-parametric-vs-one-shot"},{"id":"programmatic-design/why-programmatic/s05-05-the-classifier"},{"id":"programmatic-design/why-programmatic/s06-06-write-classify-video-task"},{"id":"programmatic-design/why-programmatic/s07-07-checkpoint"}]},{"slug":"hyperframes-and-remotion","steps":[{"id":"programmatic-design/hyperframes-and-remotion/s01-01-the-two-tools"},{"id":"programmatic-design/hyperframes-and-remotion/s02-02-hyperframes-tour"},{"id":"programmatic-design/hyperframes-and-remotion/s03-03-hyperframes-cli"},{"id":"programmatic-design/hyperframes-and-remotion/s04-04-remotion-tour"},{"id":"programmatic-design/hyperframes-and-remotion/s05-05-the-decision-tree"},{"id":"programmatic-design/hyperframes-and-remotion/s06-06-pick-the-tool"},{"id":"programmatic-design/hyperframes-and-remotion/s07-07-claude-design-html"},{"id":"programmatic-design/hyperframes-and-remotion/s08-08-write-pick-tool"},{"id":"programmatic-design/hyperframes-and-remotion/s09-09-checkpoint"}]},{"slug":"the-ai-native-design-pipeline","steps":[{"id":"programmatic-design/the-ai-native-design-pipeline/s01-01-the-seven-steps"},{"id":"programmatic-design/the-ai-native-design-pipeline/s02-02-where-ai-fits-each-step"},{"id":"programmatic-design/the-ai-native-design-pipeline/s03-03-which-model-which-step"},{"id":"programmatic-design/the-ai-native-design-pipeline/s04-04-website-to-hyperframes"},{"id":"programmatic-design/the-ai-native-design-pipeline/s05-05-the-cost-model"},{"id":"programmatic-design/the-ai-native-design-pipeline/s06-06-score-the-pipeline"},{"id":"programmatic-design/the-ai-native-design-pipeline/s07-07-write-score-pipeline"},{"id":"programmatic-design/the-ai-native-design-pipeline/s08-08-checkpoint"}]}]},{"slug":"harness-engineering","lessons":[{"slug":"the-harness-engineering-mindset","steps":[{"id":"harness-engineering/the-harness-engineering-mindset/s01-01-the-model-is-only-one-input"},{"id":"harness-engineering/the-harness-engineering-mindset/s02-02-the-six-pieces-of-a-harness"},{"id":"harness-engineering/the-harness-engineering-mindset/s03-03-which-piece-is-missing"},{"id":"harness-engineering/the-harness-engineering-mindset/s04-04-the-skill-issue-reframe"},{"id":"harness-engineering/the-harness-engineering-mindset/s05-05-pick-the-fix"},{"id":"harness-engineering/the-harness-engineering-mindset/s06-06-the-harness-gap"},{"id":"harness-engineering/the-harness-engineering-mindset/s07-07-write-the-harness-inventory"},{"id":"harness-engineering/the-harness-engineering-mindset/s08-08-checkpoint"}]},{"slug":"the-ratchet","steps":[{"id":"harness-engineering/the-ratchet/s01-01-failures-are-signals-not-flukes"},{"id":"harness-engineering/the-ratchet/s02-02-every-line-traces-to-a-failure"},{"id":"harness-engineering/the-ratchet/s03-03-which-rule-earned-its-line"},{"id":"harness-engineering/the-ratchet/s04-04-working-backwards-from-behavior"},{"id":"harness-engineering/the-ratchet/s05-05-the-ratchet-log"},{"id":"harness-engineering/the-ratchet/s06-06-spot-the-cruft"},{"id":"harness-engineering/the-ratchet/s07-07-write-the-ratchet-update"},{"id":"harness-engineering/the-ratchet/s08-08-audit-the-ratchet"},{"id":"harness-engineering/the-ratchet/s09-09-checkpoint"}]},{"slug":"context-engineering","steps":[{"id":"harness-engineering/context-engineering/s01-01-the-context-rot"},{"id":"harness-engineering/context-engineering/s02-02-compaction"},{"id":"harness-engineering/context-engineering/s03-03-tool-call-offloading"},{"id":"harness-engineering/context-engineering/s04-04-progressive-disclosure"},{"id":"harness-engineering/context-engineering/s05-05-which-technique-fits"},{"id":"harness-engineering/context-engineering/s06-06-the-memory-hierarchy"},{"id":"harness-engineering/context-engineering/s07-07-classify-the-data"},{"id":"harness-engineering/context-engineering/s08-08-write-the-context-budget"},{"id":"harness-engineering/context-engineering/s09-09-checkpoint"}]},{"slug":"long-horizon-execution","steps":[{"id":"harness-engineering/long-horizon-execution/s01-01-the-40-step-problem"},{"id":"harness-engineering/long-horizon-execution/s02-02-loops-intercepting-early-stops"},{"id":"harness-engineering/long-horizon-execution/s03-03-planning-as-a-separate-step"},{"id":"harness-engineering/long-horizon-execution/s04-04-splits-generation-vs-evaluation"},{"id":"harness-engineering/long-horizon-execution/s05-05-which-pattern-fixes-the-failure"},{"id":"harness-engineering/long-horizon-execution/s06-06-hooks-as-the-enforcement-layer"},{"id":"harness-engineering/long-horizon-execution/s07-07-the-type-check-backpressure-pattern"},{"id":"harness-engineering/long-horizon-execution/s08-08-write-the-hook-router"},{"id":"harness-engineering/long-horizon-execution/s09-09-write-the-completion-guard"},{"id":"harness-engineering/long-horizon-execution/s10-10-checkpoint"}]},{"slug":"the-haas-shift","steps":[{"id":"harness-engineering/the-haas-shift/s01-01-llm-apis-to-harness-apis"},{"id":"harness-engineering/the-haas-shift/s02-02-the-convergence"},{"id":"harness-engineering/the-haas-shift/s03-03-which-haas-fits"},{"id":"harness-engineering/the-haas-shift/s04-04-harnesses-dont-shrink-they-move"},{"id":"harness-engineering/the-haas-shift/s05-05-the-overfitting-feedback-loop"},{"id":"harness-engineering/the-haas-shift/s06-06-mcp-security-as-prompt-injection"},{"id":"harness-engineering/the-haas-shift/s07-07-which-component-is-debt"},{"id":"harness-engineering/the-haas-shift/s08-08-write-the-build-vs-buy"},{"id":"harness-engineering/the-haas-shift/s09-09-checkpoint"}]},{"slug":"pipeline-boundaries","steps":[{"id":"harness-engineering/pipeline-boundaries/s01-01-the-boundary-is-an-artifact"},{"id":"harness-engineering/pipeline-boundaries/s02-02-spot-the-risky-handoff"},{"id":"harness-engineering/pipeline-boundaries/s03-03-predict-the-gate"},{"id":"harness-engineering/pipeline-boundaries/s04-04-fill-the-gate"},{"id":"harness-engineering/pipeline-boundaries/s05-05-fix-the-overtrust"},{"id":"harness-engineering/pipeline-boundaries/s06-06-write-the-advance-check"},{"id":"harness-engineering/pipeline-boundaries/s07-07-checkpoint"}]}]},{"slug":"intro-to-terminal","lessons":[{"slug":"what-the-terminal-is","steps":[{"id":"intro-to-terminal/what-the-terminal-is/s01-01-not-a-cockpit"},{"id":"intro-to-terminal/what-the-terminal-is/s02-02-what-it-actually-is"},{"id":"intro-to-terminal/what-the-terminal-is/s03-03-open-it"},{"id":"intro-to-terminal/what-the-terminal-is/s04-04-which-app"},{"id":"intro-to-terminal/what-the-terminal-is/s05-05-the-prompt"},{"id":"intro-to-terminal/what-the-terminal-is/s06-06-what-a-command-is"},{"id":"intro-to-terminal/what-the-terminal-is/s07-07-checkpoint"}]},{"slug":"moving-around","steps":[{"id":"intro-to-terminal/moving-around/s01-01-the-filesystem-is-a-tree"},{"id":"intro-to-terminal/moving-around/s02-02-pwd-and-ls"},{"id":"intro-to-terminal/moving-around/s03-03-where-am-i"},{"id":"intro-to-terminal/moving-around/s04-04-read-this-listing"},{"id":"intro-to-terminal/moving-around/s05-05-cd"},{"id":"intro-to-terminal/moving-around/s06-06-follow-the-moves"},{"id":"intro-to-terminal/moving-around/s07-07-pick-the-command"},{"id":"intro-to-terminal/moving-around/s08-08-checkpoint"}]},{"slug":"making-things","steps":[{"id":"intro-to-terminal/making-things/s01-01-mkdir-and-touch"},{"id":"intro-to-terminal/making-things/s02-02-folder-or-file"},{"id":"intro-to-terminal/making-things/s03-03-cat-and-echo"},{"id":"intro-to-terminal/making-things/s04-04-reading-a-file"},{"id":"intro-to-terminal/making-things/s05-05-rm-carefully"},{"id":"intro-to-terminal/making-things/s06-06-the-no-undo-rule"},{"id":"intro-to-terminal/making-things/s07-07-string-it-together"},{"id":"intro-to-terminal/making-things/s08-08-checkpoint"}]}]},{"slug":"intro-to-claude-cli","lessons":[{"slug":"what-the-claude-cli-is","steps":[{"id":"intro-to-claude-cli/what-the-claude-cli-is/s01-01-the-glass-is-gone"},{"id":"intro-to-claude-cli/what-the-claude-cli-is/s02-02-chat-vs-cli"},{"id":"intro-to-claude-cli/what-the-claude-cli-is/s03-03-which-tool"},{"id":"intro-to-claude-cli/what-the-claude-cli-is/s04-04-the-agent-loop"},{"id":"intro-to-claude-cli/what-the-claude-cli-is/s05-05-read-the-loop"},{"id":"intro-to-claude-cli/what-the-claude-cli-is/s06-06-permission-and-limits"},{"id":"intro-to-claude-cli/what-the-claude-cli-is/s07-07-checkpoint"}]},{"slug":"install-and-sign-in","steps":[{"id":"intro-to-claude-cli/install-and-sign-in/s01-01-two-ways-to-install"},{"id":"intro-to-claude-cli/install-and-sign-in/s02-02-run-the-installer"},{"id":"intro-to-claude-cli/install-and-sign-in/s03-03-install-check"},{"id":"intro-to-claude-cli/install-and-sign-in/s04-04-sign-in"},{"id":"intro-to-claude-cli/install-and-sign-in/s05-05-what-sign-in-did"},{"id":"intro-to-claude-cli/install-and-sign-in/s06-06-auth-check"},{"id":"intro-to-claude-cli/install-and-sign-in/s07-07-account-not-api-key"},{"id":"intro-to-claude-cli/install-and-sign-in/s08-08-checkpoint"}]},{"slug":"your-first-session","steps":[{"id":"intro-to-claude-cli/your-first-session/s01-01-start-in-a-folder"},{"id":"intro-to-claude-cli/your-first-session/s02-02-your-first-instruction"},{"id":"intro-to-claude-cli/your-first-session/s03-03-watch-the-loop"},{"id":"intro-to-claude-cli/your-first-session/s04-04-read-what-it-did"},{"id":"intro-to-claude-cli/your-first-session/s05-05-one-shot-or-interactive"},{"id":"intro-to-claude-cli/your-first-session/s06-06-chat-or-cli-decision"},{"id":"intro-to-claude-cli/your-first-session/s07-07-where-this-goes"},{"id":"intro-to-claude-cli/your-first-session/s08-08-checkpoint"}]}]},{"slug":"intro-to-codex-cli","lessons":[{"slug":"another-tool-same-idea","steps":[{"id":"intro-to-codex-cli/another-tool-same-idea/s01-01-why-a-second-tool"},{"id":"intro-to-codex-cli/another-tool-same-idea/s02-02-what-carries-over"},{"id":"intro-to-codex-cli/another-tool-same-idea/s03-03-what-carries-over-check"},{"id":"intro-to-codex-cli/another-tool-same-idea/s04-04-what-is-different"},{"id":"intro-to-codex-cli/another-tool-same-idea/s05-05-spot-the-difference"},{"id":"intro-to-codex-cli/another-tool-same-idea/s06-06-when-to-reach-for-which"},{"id":"intro-to-codex-cli/another-tool-same-idea/s07-07-checkpoint"}]},{"slug":"install-and-sign-in","steps":[{"id":"intro-to-codex-cli/install-and-sign-in/s01-01-the-install-paths"},{"id":"intro-to-codex-cli/install-and-sign-in/s02-02-installing-it"},{"id":"intro-to-codex-cli/install-and-sign-in/s03-03-verify-it"},{"id":"intro-to-codex-cli/install-and-sign-in/s04-04-install-check"},{"id":"intro-to-codex-cli/install-and-sign-in/s05-05-sign-in"},{"id":"intro-to-codex-cli/install-and-sign-in/s06-06-account-vs-api-key"},{"id":"intro-to-codex-cli/install-and-sign-in/s07-07-auth-check"},{"id":"intro-to-codex-cli/install-and-sign-in/s08-08-checkpoint"}]},{"slug":"your-first-session","steps":[{"id":"intro-to-codex-cli/your-first-session/s01-01-start-and-instruct"},{"id":"intro-to-codex-cli/your-first-session/s02-02-the-loop-again"},{"id":"intro-to-codex-cli/your-first-session/s03-03-read-what-it-did"},{"id":"intro-to-codex-cli/your-first-session/s04-04-usage-patterns"},{"id":"intro-to-codex-cli/your-first-session/s05-05-usage-scenario"},{"id":"intro-to-codex-cli/your-first-session/s06-06-running-both"},{"id":"intro-to-codex-cli/your-first-session/s07-07-where-this-goes"},{"id":"intro-to-codex-cli/your-first-session/s08-08-checkpoint"}]}]},{"slug":"team-skills","lessons":[{"slug":"what-a-skill-is","steps":[{"id":"team-skills/what-a-skill-is/s01-01-the-re-explaining-problem"},{"id":"team-skills/what-a-skill-is/s02-02-a-skill-defined"},{"id":"team-skills/what-a-skill-is/s03-03-a-real-skill"},{"id":"team-skills/what-a-skill-is/s04-04-what-a-skill-is-check"},{"id":"team-skills/what-a-skill-is/s05-05-skill-vs-prompt-vs-agent"},{"id":"team-skills/what-a-skill-is/s06-06-skill-or-agent"},{"id":"team-skills/what-a-skill-is/s07-07-checkpoint"}]},{"slug":"skills-as-a-team-thing","steps":[{"id":"team-skills/skills-as-a-team-thing/s01-01-the-team-problem"},{"id":"team-skills/skills-as-a-team-thing/s02-02-org-wide-skills"},{"id":"team-skills/skills-as-a-team-thing/s03-03-sharing-and-the-directory"},{"id":"team-skills/skills-as-a-team-thing/s04-04-deployment-check"},{"id":"team-skills/skills-as-a-team-thing/s05-05-collaborating-through-skills"},{"id":"team-skills/skills-as-a-team-thing/s06-06-sharing-scenario"},{"id":"team-skills/skills-as-a-team-thing/s07-07-checkpoint"}]},{"slug":"role-playbooks","steps":[{"id":"team-skills/role-playbooks/s01-01-hr-skills"},{"id":"team-skills/role-playbooks/s02-02-legal-skills"},{"id":"team-skills/role-playbooks/s03-03-operations-skills"},{"id":"team-skills/role-playbooks/s04-04-match-the-skill"},{"id":"team-skills/role-playbooks/s05-05-skill-or-one-off"},{"id":"team-skills/role-playbooks/s06-06-skill-or-one-off-check"},{"id":"team-skills/role-playbooks/s07-07-checkpoint"}]},{"slug":"governance-and-trust","steps":[{"id":"team-skills/governance-and-trust/s01-01-a-skill-can-do-real-things"},{"id":"team-skills/governance-and-trust/s02-02-treat-it-like-software"},{"id":"team-skills/governance-and-trust/s03-03-evaluate-before-you-deploy"},{"id":"team-skills/governance-and-trust/s04-04-access-control"},{"id":"team-skills/governance-and-trust/s05-05-governance-scenario"},{"id":"team-skills/governance-and-trust/s06-06-a-rollout-checklist"},{"id":"team-skills/governance-and-trust/s07-07-checkpoint"}]}]},{"slug":"dataframes-numpy-pandas","lessons":[{"slug":"ml-package-map","steps":[{"id":"dataframes-numpy-pandas/ml-package-map/s01-01-intro"},{"id":"dataframes-numpy-pandas/ml-package-map/s02-02-match-the-tool"},{"id":"dataframes-numpy-pandas/ml-package-map/s03-03-predict-sys-modules"},{"id":"dataframes-numpy-pandas/ml-package-map/s04-04-fill-the-registry-key"},{"id":"dataframes-numpy-pandas/ml-package-map/s05-05-fix-the-swapped-map"},{"id":"dataframes-numpy-pandas/ml-package-map/s06-06-write-find-unused"},{"id":"dataframes-numpy-pandas/ml-package-map/s07-07-checkpoint"}]},{"slug":"array-and-series-shapes","steps":[{"id":"dataframes-numpy-pandas/array-and-series-shapes/s01-01-intro"},{"id":"dataframes-numpy-pandas/array-and-series-shapes/s02-02-choose-the-risk"},{"id":"dataframes-numpy-pandas/array-and-series-shapes/s03-03-predict-the-checks"},{"id":"dataframes-numpy-pandas/array-and-series-shapes/s04-04-fill-the-return"},{"id":"dataframes-numpy-pandas/array-and-series-shapes/s05-05-fix-the-overtrust"},{"id":"dataframes-numpy-pandas/array-and-series-shapes/s06-06-write-count-ready"},{"id":"dataframes-numpy-pandas/array-and-series-shapes/s07-07-checkpoint"}]},{"slug":"dataframe-selection-and-cleaning","steps":[{"id":"dataframes-numpy-pandas/dataframe-selection-and-cleaning/s01-01-intro"},{"id":"dataframes-numpy-pandas/dataframe-selection-and-cleaning/s02-02-choose-the-risk"},{"id":"dataframes-numpy-pandas/dataframe-selection-and-cleaning/s03-03-predict-the-checks"},{"id":"dataframes-numpy-pandas/dataframe-selection-and-cleaning/s04-04-fill-the-return"},{"id":"dataframes-numpy-pandas/dataframe-selection-and-cleaning/s05-05-fix-the-overtrust"},{"id":"dataframes-numpy-pandas/dataframe-selection-and-cleaning/s06-06-write-count-ready"},{"id":"dataframes-numpy-pandas/dataframe-selection-and-cleaning/s07-07-checkpoint"}]},{"slug":"missing-values-and-types","steps":[{"id":"dataframes-numpy-pandas/missing-values-and-types/s01-01-intro"},{"id":"dataframes-numpy-pandas/missing-values-and-types/s02-02-choose-the-risk"},{"id":"dataframes-numpy-pandas/missing-values-and-types/s03-03-predict-the-checks"},{"id":"dataframes-numpy-pandas/missing-values-and-types/s04-04-fill-the-return"},{"id":"dataframes-numpy-pandas/missing-values-and-types/s05-05-fix-the-overtrust"},{"id":"dataframes-numpy-pandas/missing-values-and-types/s06-06-write-count-ready"},{"id":"dataframes-numpy-pandas/missing-values-and-types/s07-07-checkpoint"}]},{"slug":"groupby-joins-and-features","steps":[{"id":"dataframes-numpy-pandas/groupby-joins-and-features/s01-01-intro"},{"id":"dataframes-numpy-pandas/groupby-joins-and-features/s02-02-choose-the-risk"},{"id":"dataframes-numpy-pandas/groupby-joins-and-features/s03-03-predict-the-checks"},{"id":"dataframes-numpy-pandas/groupby-joins-and-features/s04-04-fill-the-return"},{"id":"dataframes-numpy-pandas/groupby-joins-and-features/s05-05-fix-the-overtrust"},{"id":"dataframes-numpy-pandas/groupby-joins-and-features/s06-06-write-count-ready"},{"id":"dataframes-numpy-pandas/groupby-joins-and-features/s07-07-checkpoint"}]},{"slug":"mission-api-to-dataframe","steps":[{"id":"dataframes-numpy-pandas/mission-api-to-dataframe/s01-01-intro"},{"id":"dataframes-numpy-pandas/mission-api-to-dataframe/s02-02-choose-the-risk"},{"id":"dataframes-numpy-pandas/mission-api-to-dataframe/s03-03-predict-the-checks"},{"id":"dataframes-numpy-pandas/mission-api-to-dataframe/s04-04-fill-the-return"},{"id":"dataframes-numpy-pandas/mission-api-to-dataframe/s05-05-fix-the-overtrust"},{"id":"dataframes-numpy-pandas/mission-api-to-dataframe/s06-06-write-count-ready"},{"id":"dataframes-numpy-pandas/mission-api-to-dataframe/s07-07-checkpoint"}]}]},{"slug":"sql-for-ml-datasets","lessons":[{"slug":"select-filter-aggregate","steps":[{"id":"sql-for-ml-datasets/select-filter-aggregate/s01-01-intro"},{"id":"sql-for-ml-datasets/select-filter-aggregate/s02-02-choose-the-risk"},{"id":"sql-for-ml-datasets/select-filter-aggregate/s03-03-predict-the-checks"},{"id":"sql-for-ml-datasets/select-filter-aggregate/s04-04-fill-the-return"},{"id":"sql-for-ml-datasets/select-filter-aggregate/s05-05-fix-the-overtrust"},{"id":"sql-for-ml-datasets/select-filter-aggregate/s06-06-write-count-ready"},{"id":"sql-for-ml-datasets/select-filter-aggregate/s07-07-checkpoint"}]},{"slug":"joins-and-label-windows","steps":[{"id":"sql-for-ml-datasets/joins-and-label-windows/s01-01-intro"},{"id":"sql-for-ml-datasets/joins-and-label-windows/s02-02-choose-the-risk"},{"id":"sql-for-ml-datasets/joins-and-label-windows/s03-03-predict-the-checks"},{"id":"sql-for-ml-datasets/joins-and-label-windows/s04-04-fill-the-return"},{"id":"sql-for-ml-datasets/joins-and-label-windows/s05-05-fix-the-overtrust"},{"id":"sql-for-ml-datasets/joins-and-label-windows/s06-06-write-count-ready"},{"id":"sql-for-ml-datasets/joins-and-label-windows/s07-07-checkpoint"}]},{"slug":"sql-quality-checks","steps":[{"id":"sql-for-ml-datasets/sql-quality-checks/s01-01-intro"},{"id":"sql-for-ml-datasets/sql-quality-checks/s02-02-choose-the-risk"},{"id":"sql-for-ml-datasets/sql-quality-checks/s03-03-predict-the-checks"},{"id":"sql-for-ml-datasets/sql-quality-checks/s04-04-fill-the-return"},{"id":"sql-for-ml-datasets/sql-quality-checks/s05-05-fix-the-overtrust"},{"id":"sql-for-ml-datasets/sql-quality-checks/s06-06-write-count-ready"},{"id":"sql-for-ml-datasets/sql-quality-checks/s07-07-checkpoint"}]},{"slug":"mission-sql-feature-query-lab","steps":[{"id":"sql-for-ml-datasets/mission-sql-feature-query-lab/s01-01-intro"},{"id":"sql-for-ml-datasets/mission-sql-feature-query-lab/s02-02-choose-the-risk"},{"id":"sql-for-ml-datasets/mission-sql-feature-query-lab/s03-03-predict-the-checks"},{"id":"sql-for-ml-datasets/mission-sql-feature-query-lab/s04-04-fill-the-return"},{"id":"sql-for-ml-datasets/mission-sql-feature-query-lab/s05-05-fix-the-overtrust"},{"id":"sql-for-ml-datasets/mission-sql-feature-query-lab/s06-06-write-count-ready"},{"id":"sql-for-ml-datasets/mission-sql-feature-query-lab/s07-07-checkpoint"}]}]},{"slug":"dataset-pipelines","lessons":[{"slug":"csv-jsonl-parquet-tradeoffs","steps":[{"id":"dataset-pipelines/csv-jsonl-parquet-tradeoffs/s01-01-intro"},{"id":"dataset-pipelines/csv-jsonl-parquet-tradeoffs/s02-02-choose-the-risk"},{"id":"dataset-pipelines/csv-jsonl-parquet-tradeoffs/s03-03-predict-the-checks"},{"id":"dataset-pipelines/csv-jsonl-parquet-tradeoffs/s04-04-fill-the-return"},{"id":"dataset-pipelines/csv-jsonl-parquet-tradeoffs/s05-05-fix-the-overtrust"},{"id":"dataset-pipelines/csv-jsonl-parquet-tradeoffs/s06-06-write-count-ready"},{"id":"dataset-pipelines/csv-jsonl-parquet-tradeoffs/s07-07-checkpoint"}]},{"slug":"pagination-retries-checkpoints","steps":[{"id":"dataset-pipelines/pagination-retries-checkpoints/s01-01-intro"},{"id":"dataset-pipelines/pagination-retries-checkpoints/s02-02-choose-the-risk"},{"id":"dataset-pipelines/pagination-retries-checkpoints/s03-03-predict-the-checks"},{"id":"dataset-pipelines/pagination-retries-checkpoints/s04-04-fill-the-return"},{"id":"dataset-pipelines/pagination-retries-checkpoints/s05-05-fix-the-overtrust"},{"id":"dataset-pipelines/pagination-retries-checkpoints/s06-06-write-count-ready"},{"id":"dataset-pipelines/pagination-retries-checkpoints/s07-07-checkpoint"}]},{"slug":"schema-drift-and-contracts","steps":[{"id":"dataset-pipelines/schema-drift-and-contracts/s01-01-intro"},{"id":"dataset-pipelines/schema-drift-and-contracts/s02-02-choose-the-risk"},{"id":"dataset-pipelines/schema-drift-and-contracts/s03-03-predict-the-checks"},{"id":"dataset-pipelines/schema-drift-and-contracts/s04-04-fill-the-return"},{"id":"dataset-pipelines/schema-drift-and-contracts/s05-05-fix-the-overtrust"},{"id":"dataset-pipelines/schema-drift-and-contracts/s06-06-write-count-ready"},{"id":"dataset-pipelines/schema-drift-and-contracts/s07-07-checkpoint"}]},{"slug":"pipeline-orchestration-shape","steps":[{"id":"dataset-pipelines/pipeline-orchestration-shape/s01-01-intro"},{"id":"dataset-pipelines/pipeline-orchestration-shape/s02-02-choose-the-risk"},{"id":"dataset-pipelines/pipeline-orchestration-shape/s03-03-predict-the-checks"},{"id":"dataset-pipelines/pipeline-orchestration-shape/s04-04-fill-the-return"},{"id":"dataset-pipelines/pipeline-orchestration-shape/s05-05-fix-the-overtrust"},{"id":"dataset-pipelines/pipeline-orchestration-shape/s06-06-write-count-ready"},{"id":"dataset-pipelines/pipeline-orchestration-shape/s07-07-checkpoint"}]},{"slug":"mission-api-to-dataset-pipeline","steps":[{"id":"dataset-pipelines/mission-api-to-dataset-pipeline/s01-01-intro"},{"id":"dataset-pipelines/mission-api-to-dataset-pipeline/s02-02-choose-the-risk"},{"id":"dataset-pipelines/mission-api-to-dataset-pipeline/s03-03-predict-the-checks"},{"id":"dataset-pipelines/mission-api-to-dataset-pipeline/s04-04-fill-the-return"},{"id":"dataset-pipelines/mission-api-to-dataset-pipeline/s05-05-fix-the-overtrust"},{"id":"dataset-pipelines/mission-api-to-dataset-pipeline/s06-06-write-count-ready"},{"id":"dataset-pipelines/mission-api-to-dataset-pipeline/s07-07-checkpoint"}]}]},{"slug":"ml-math-and-stats","lessons":[{"slug":"vectors-matrices-dot-products","steps":[{"id":"ml-math-and-stats/vectors-matrices-dot-products/s01-01-intro"},{"id":"ml-math-and-stats/vectors-matrices-dot-products/s02-02-choose-the-risk"},{"id":"ml-math-and-stats/vectors-matrices-dot-products/s03-03-predict-the-checks"},{"id":"ml-math-and-stats/vectors-matrices-dot-products/s04-04-fill-the-return"},{"id":"ml-math-and-stats/vectors-matrices-dot-products/s05-05-fix-the-overtrust"},{"id":"ml-math-and-stats/vectors-matrices-dot-products/s06-06-write-count-ready"},{"id":"ml-math-and-stats/vectors-matrices-dot-products/s07-07-checkpoint"}]},{"slug":"probability-and-baselines","steps":[{"id":"ml-math-and-stats/probability-and-baselines/s01-01-intro"},{"id":"ml-math-and-stats/probability-and-baselines/s02-02-choose-the-risk"},{"id":"ml-math-and-stats/probability-and-baselines/s03-03-predict-the-checks"},{"id":"ml-math-and-stats/probability-and-baselines/s04-04-fill-the-return"},{"id":"ml-math-and-stats/probability-and-baselines/s05-05-fix-the-overtrust"},{"id":"ml-math-and-stats/probability-and-baselines/s06-06-write-count-ready"},{"id":"ml-math-and-stats/probability-and-baselines/s07-07-checkpoint"}]},{"slug":"distributions-sampling-variance","steps":[{"id":"ml-math-and-stats/distributions-sampling-variance/s01-01-intro"},{"id":"ml-math-and-stats/distributions-sampling-variance/s02-02-choose-the-risk"},{"id":"ml-math-and-stats/distributions-sampling-variance/s03-03-predict-the-checks"},{"id":"ml-math-and-stats/distributions-sampling-variance/s04-04-fill-the-return"},{"id":"ml-math-and-stats/distributions-sampling-variance/s05-05-fix-the-overtrust"},{"id":"ml-math-and-stats/distributions-sampling-variance/s06-06-write-variance"},{"id":"ml-math-and-stats/distributions-sampling-variance/s07-07-checkpoint"}]},{"slug":"bias-variance-and-leakage","steps":[{"id":"ml-math-and-stats/bias-variance-and-leakage/s01-01-intro"},{"id":"ml-math-and-stats/bias-variance-and-leakage/s02-02-choose-the-risk"},{"id":"ml-math-and-stats/bias-variance-and-leakage/s03-03-predict-the-checks"},{"id":"ml-math-and-stats/bias-variance-and-leakage/s04-04-fill-the-return"},{"id":"ml-math-and-stats/bias-variance-and-leakage/s05-05-fix-the-overtrust"},{"id":"ml-math-and-stats/bias-variance-and-leakage/s06-06-write-diagnose"},{"id":"ml-math-and-stats/bias-variance-and-leakage/s07-07-checkpoint"}]},{"slug":"mission-statistical-sanity-check","steps":[{"id":"ml-math-and-stats/mission-statistical-sanity-check/s01-01-intro"},{"id":"ml-math-and-stats/mission-statistical-sanity-check/s02-02-choose-the-risk"},{"id":"ml-math-and-stats/mission-statistical-sanity-check/s03-03-predict-the-checks"},{"id":"ml-math-and-stats/mission-statistical-sanity-check/s04-04-fill-the-return"},{"id":"ml-math-and-stats/mission-statistical-sanity-check/s05-05-fix-the-overtrust"},{"id":"ml-math-and-stats/mission-statistical-sanity-check/s06-06-write-count-ready"},{"id":"ml-math-and-stats/mission-statistical-sanity-check/s07-07-checkpoint"}]}]},{"slug":"supervised-learning-workflows","lessons":[{"slug":"labels-features-splits","steps":[{"id":"supervised-learning-workflows/labels-features-splits/s01-01-intro"},{"id":"supervised-learning-workflows/labels-features-splits/s02-02-choose-the-risk"},{"id":"supervised-learning-workflows/labels-features-splits/s03-03-predict-the-checks"},{"id":"supervised-learning-workflows/labels-features-splits/s04-04-fill-the-return"},{"id":"supervised-learning-workflows/labels-features-splits/s05-05-fix-the-overtrust"},{"id":"supervised-learning-workflows/labels-features-splits/s06-06-write-split-audit"},{"id":"supervised-learning-workflows/labels-features-splits/s07-07-checkpoint"}]},{"slug":"baselines-before-fancy-models","steps":[{"id":"supervised-learning-workflows/baselines-before-fancy-models/s01-01-intro"},{"id":"supervised-learning-workflows/baselines-before-fancy-models/s02-02-choose-the-risk"},{"id":"supervised-learning-workflows/baselines-before-fancy-models/s03-03-predict-the-checks"},{"id":"supervised-learning-workflows/baselines-before-fancy-models/s04-04-fill-the-return"},{"id":"supervised-learning-workflows/baselines-before-fancy-models/s05-05-fix-the-overtrust"},{"id":"supervised-learning-workflows/baselines-before-fancy-models/s06-06-write-baseline-comparison"},{"id":"supervised-learning-workflows/baselines-before-fancy-models/s07-07-checkpoint"}]},{"slug":"training-and-prediction-loop","steps":[{"id":"supervised-learning-workflows/training-and-prediction-loop/s01-01-intro"},{"id":"supervised-learning-workflows/training-and-prediction-loop/s02-02-choose-the-risk"},{"id":"supervised-learning-workflows/training-and-prediction-loop/s03-03-predict-the-checks"},{"id":"supervised-learning-workflows/training-and-prediction-loop/s04-04-fill-the-return"},{"id":"supervised-learning-workflows/training-and-prediction-loop/s05-05-fix-the-overtrust"},{"id":"supervised-learning-workflows/training-and-prediction-loop/s06-06-write-train"},{"id":"supervised-learning-workflows/training-and-prediction-loop/s07-07-checkpoint"}]},{"slug":"overfitting-and-regularization","steps":[{"id":"supervised-learning-workflows/overfitting-and-regularization/s01-01-intro"},{"id":"supervised-learning-workflows/overfitting-and-regularization/s02-02-choose-the-risk"},{"id":"supervised-learning-workflows/overfitting-and-regularization/s03-03-predict-the-checks"},{"id":"supervised-learning-workflows/overfitting-and-regularization/s04-04-fill-the-return"},{"id":"supervised-learning-workflows/overfitting-and-regularization/s05-05-fix-the-overtrust"},{"id":"supervised-learning-workflows/overfitting-and-regularization/s06-06-write-overfit-audit"},{"id":"supervised-learning-workflows/overfitting-and-regularization/s07-07-checkpoint"}]},{"slug":"mission-baseline-model-showdown","steps":[{"id":"supervised-learning-workflows/mission-baseline-model-showdown/s01-01-intro"},{"id":"supervised-learning-workflows/mission-baseline-model-showdown/s02-02-choose-the-risk"},{"id":"supervised-learning-workflows/mission-baseline-model-showdown/s03-03-predict-the-checks"},{"id":"supervised-learning-workflows/mission-baseline-model-showdown/s04-04-fill-the-return"},{"id":"supervised-learning-workflows/mission-baseline-model-showdown/s05-05-fix-the-overtrust"},{"id":"supervised-learning-workflows/mission-baseline-model-showdown/s06-06-write-classifier-brief"},{"id":"supervised-learning-workflows/mission-baseline-model-showdown/s07-07-checkpoint"}]}]},{"slug":"unsupervised-learning-and-embeddings","lessons":[{"slug":"clustering-without-labels","steps":[{"id":"unsupervised-learning-and-embeddings/clustering-without-labels/s01-01-intro"},{"id":"unsupervised-learning-and-embeddings/clustering-without-labels/s02-02-choose-the-risk"},{"id":"unsupervised-learning-and-embeddings/clustering-without-labels/s03-03-predict-the-checks"},{"id":"unsupervised-learning-and-embeddings/clustering-without-labels/s04-04-fill-the-return"},{"id":"unsupervised-learning-and-embeddings/clustering-without-labels/s05-05-fix-the-overtrust"},{"id":"unsupervised-learning-and-embeddings/clustering-without-labels/s06-06-write-cluster-summary"},{"id":"unsupervised-learning-and-embeddings/clustering-without-labels/s07-07-checkpoint"}]},{"slug":"dimensionality-and-distance","steps":[{"id":"unsupervised-learning-and-embeddings/dimensionality-and-distance/s01-01-intro"},{"id":"unsupervised-learning-and-embeddings/dimensionality-and-distance/s02-02-choose-the-risk"},{"id":"unsupervised-learning-and-embeddings/dimensionality-and-distance/s03-03-predict-the-checks"},{"id":"unsupervised-learning-and-embeddings/dimensionality-and-distance/s04-04-fill-the-return"},{"id":"unsupervised-learning-and-embeddings/dimensionality-and-distance/s05-05-fix-the-overtrust"},{"id":"unsupervised-learning-and-embeddings/dimensionality-and-distance/s06-06-write-euclidean"},{"id":"unsupervised-learning-and-embeddings/dimensionality-and-distance/s07-07-checkpoint"}]},{"slug":"embeddings-as-features","steps":[{"id":"unsupervised-learning-and-embeddings/embeddings-as-features/s01-01-intro"},{"id":"unsupervised-learning-and-embeddings/embeddings-as-features/s02-02-choose-the-risk"},{"id":"unsupervised-learning-and-embeddings/embeddings-as-features/s03-03-predict-the-checks"},{"id":"unsupervised-learning-and-embeddings/embeddings-as-features/s04-04-fill-the-return"},{"id":"unsupervised-learning-and-embeddings/embeddings-as-features/s05-05-fix-the-overtrust"},{"id":"unsupervised-learning-and-embeddings/embeddings-as-features/s06-06-write-retrieval-receipt"},{"id":"unsupervised-learning-and-embeddings/embeddings-as-features/s07-07-checkpoint"}]},{"slug":"mission-tiny-recommender","steps":[{"id":"unsupervised-learning-and-embeddings/mission-tiny-recommender/s01-01-intro"},{"id":"unsupervised-learning-and-embeddings/mission-tiny-recommender/s02-02-choose-the-risk"},{"id":"unsupervised-learning-and-embeddings/mission-tiny-recommender/s03-03-predict-the-checks"},{"id":"unsupervised-learning-and-embeddings/mission-tiny-recommender/s04-04-fill-the-return"},{"id":"unsupervised-learning-and-embeddings/mission-tiny-recommender/s05-05-fix-the-overtrust"},{"id":"unsupervised-learning-and-embeddings/mission-tiny-recommender/s06-06-write-recommendation-card"},{"id":"unsupervised-learning-and-embeddings/mission-tiny-recommender/s07-07-checkpoint"}]}]},{"slug":"metrics-and-error-analysis","lessons":[{"slug":"confusion-matrix","steps":[{"id":"metrics-and-error-analysis/confusion-matrix/s01-01-intro"},{"id":"metrics-and-error-analysis/confusion-matrix/s02-02-choose-the-risk"},{"id":"metrics-and-error-analysis/confusion-matrix/s03-03-predict-the-checks"},{"id":"metrics-and-error-analysis/confusion-matrix/s04-04-fill-the-return"},{"id":"metrics-and-error-analysis/confusion-matrix/s05-05-fix-the-overtrust"},{"id":"metrics-and-error-analysis/confusion-matrix/s06-06-write-count-ready"},{"id":"metrics-and-error-analysis/confusion-matrix/s07-07-checkpoint"}]},{"slug":"precision-recall-thresholds","steps":[{"id":"metrics-and-error-analysis/precision-recall-thresholds/s01-01-intro"},{"id":"metrics-and-error-analysis/precision-recall-thresholds/s02-02-choose-the-risk"},{"id":"metrics-and-error-analysis/precision-recall-thresholds/s03-03-predict-the-checks"},{"id":"metrics-and-error-analysis/precision-recall-thresholds/s04-04-fill-the-return"},{"id":"metrics-and-error-analysis/precision-recall-thresholds/s05-05-fix-the-overtrust"},{"id":"metrics-and-error-analysis/precision-recall-thresholds/s06-06-write-count-ready"},{"id":"metrics-and-error-analysis/precision-recall-thresholds/s07-07-checkpoint"}]},{"slug":"slice-based-error-analysis","steps":[{"id":"metrics-and-error-analysis/slice-based-error-analysis/s01-01-intro"},{"id":"metrics-and-error-analysis/slice-based-error-analysis/s02-02-choose-the-risk"},{"id":"metrics-and-error-analysis/slice-based-error-analysis/s03-03-predict-the-checks"},{"id":"metrics-and-error-analysis/slice-based-error-analysis/s04-04-fill-the-return"},{"id":"metrics-and-error-analysis/slice-based-error-analysis/s05-05-fix-the-overtrust"},{"id":"metrics-and-error-analysis/slice-based-error-analysis/s06-06-write-count-ready"},{"id":"metrics-and-error-analysis/slice-based-error-analysis/s07-07-checkpoint"}]},{"slug":"regression-metrics-and-residuals","steps":[{"id":"metrics-and-error-analysis/regression-metrics-and-residuals/s01-01-intro"},{"id":"metrics-and-error-analysis/regression-metrics-and-residuals/s02-02-choose-the-risk"},{"id":"metrics-and-error-analysis/regression-metrics-and-residuals/s03-03-predict-the-checks"},{"id":"metrics-and-error-analysis/regression-metrics-and-residuals/s04-04-fill-the-return"},{"id":"metrics-and-error-analysis/regression-metrics-and-residuals/s05-05-fix-the-overtrust"},{"id":"metrics-and-error-analysis/regression-metrics-and-residuals/s06-06-write-count-ready"},{"id":"metrics-and-error-analysis/regression-metrics-and-residuals/s07-07-checkpoint"}]},{"slug":"mission-confusion-matrix-triage","steps":[{"id":"metrics-and-error-analysis/mission-confusion-matrix-triage/s01-01-intro"},{"id":"metrics-and-error-analysis/mission-confusion-matrix-triage/s02-02-choose-the-risk"},{"id":"metrics-and-error-analysis/mission-confusion-matrix-triage/s03-03-predict-the-checks"},{"id":"metrics-and-error-analysis/mission-confusion-matrix-triage/s04-04-fill-the-return"},{"id":"metrics-and-error-analysis/mission-confusion-matrix-triage/s05-05-fix-the-overtrust"},{"id":"metrics-and-error-analysis/mission-confusion-matrix-triage/s06-06-write-count-ready"},{"id":"metrics-and-error-analysis/mission-confusion-matrix-triage/s07-07-checkpoint"}]}]},{"slug":"pytorch-tensors-and-autograd","lessons":[{"slug":"tensors-and-shapes","steps":[{"id":"pytorch-tensors-and-autograd/tensors-and-shapes/s01-01-intro"},{"id":"pytorch-tensors-and-autograd/tensors-and-shapes/s02-02-choose-the-risk"},{"id":"pytorch-tensors-and-autograd/tensors-and-shapes/s03-03-predict-the-checks"},{"id":"pytorch-tensors-and-autograd/tensors-and-shapes/s04-04-fill-the-return"},{"id":"pytorch-tensors-and-autograd/tensors-and-shapes/s05-05-fix-the-overtrust"},{"id":"pytorch-tensors-and-autograd/tensors-and-shapes/s06-06-write-count-ready"},{"id":"pytorch-tensors-and-autograd/tensors-and-shapes/s07-07-checkpoint"}]},{"slug":"broadcasting-and-vectorization","steps":[{"id":"pytorch-tensors-and-autograd/broadcasting-and-vectorization/s01-01-intro"},{"id":"pytorch-tensors-and-autograd/broadcasting-and-vectorization/s02-02-choose-the-risk"},{"id":"pytorch-tensors-and-autograd/broadcasting-and-vectorization/s03-03-predict-the-checks"},{"id":"pytorch-tensors-and-autograd/broadcasting-and-vectorization/s04-04-fill-the-return"},{"id":"pytorch-tensors-and-autograd/broadcasting-and-vectorization/s05-05-fix-the-overtrust"},{"id":"pytorch-tensors-and-autograd/broadcasting-and-vectorization/s06-06-write-count-ready"},{"id":"pytorch-tensors-and-autograd/broadcasting-and-vectorization/s07-07-checkpoint"}]},{"slug":"autograd-mental-model","steps":[{"id":"pytorch-tensors-and-autograd/autograd-mental-model/s01-01-intro"},{"id":"pytorch-tensors-and-autograd/autograd-mental-model/s02-02-choose-the-risk"},{"id":"pytorch-tensors-and-autograd/autograd-mental-model/s03-03-predict-the-checks"},{"id":"pytorch-tensors-and-autograd/autograd-mental-model/s04-04-fill-the-return"},{"id":"pytorch-tensors-and-autograd/autograd-mental-model/s05-05-fix-the-overtrust"},{"id":"pytorch-tensors-and-autograd/autograd-mental-model/s06-06-write-count-ready"},{"id":"pytorch-tensors-and-autograd/autograd-mental-model/s07-07-checkpoint"}]},{"slug":"mission-tensor-playground","steps":[{"id":"pytorch-tensors-and-autograd/mission-tensor-playground/s01-01-intro"},{"id":"pytorch-tensors-and-autograd/mission-tensor-playground/s02-02-choose-the-risk"},{"id":"pytorch-tensors-and-autograd/mission-tensor-playground/s03-03-predict-the-checks"},{"id":"pytorch-tensors-and-autograd/mission-tensor-playground/s04-04-fill-the-return"},{"id":"pytorch-tensors-and-autograd/mission-tensor-playground/s05-05-fix-the-overtrust"},{"id":"pytorch-tensors-and-autograd/mission-tensor-playground/s06-06-write-count-ready"},{"id":"pytorch-tensors-and-autograd/mission-tensor-playground/s07-07-checkpoint"}]}]},{"slug":"training-loops-and-optimizers","lessons":[{"slug":"loss-forward-backward-step","steps":[{"id":"training-loops-and-optimizers/loss-forward-backward-step/s01-01-intro"},{"id":"training-loops-and-optimizers/loss-forward-backward-step/s02-02-choose-the-risk"},{"id":"training-loops-and-optimizers/loss-forward-backward-step/s03-03-predict-the-checks"},{"id":"training-loops-and-optimizers/loss-forward-backward-step/s04-04-fill-the-return"},{"id":"training-loops-and-optimizers/loss-forward-backward-step/s05-05-fix-the-overtrust"},{"id":"training-loops-and-optimizers/loss-forward-backward-step/s06-06-write-count-ready"},{"id":"training-loops-and-optimizers/loss-forward-backward-step/s07-07-checkpoint"}]},{"slug":"gradient-descent-by-hand","steps":[{"id":"training-loops-and-optimizers/gradient-descent-by-hand/s01-01-intro"},{"id":"training-loops-and-optimizers/gradient-descent-by-hand/s02-02-choose-the-risk"},{"id":"training-loops-and-optimizers/gradient-descent-by-hand/s03-03-predict-the-checks"},{"id":"training-loops-and-optimizers/gradient-descent-by-hand/s04-04-fill-the-return"},{"id":"training-loops-and-optimizers/gradient-descent-by-hand/s05-05-fix-the-overtrust"},{"id":"training-loops-and-optimizers/gradient-descent-by-hand/s06-06-write-count-ready"},{"id":"training-loops-and-optimizers/gradient-descent-by-hand/s07-07-checkpoint"}]},{"slug":"optimizers-and-schedulers","steps":[{"id":"training-loops-and-optimizers/optimizers-and-schedulers/s01-01-intro"},{"id":"training-loops-and-optimizers/optimizers-and-schedulers/s02-02-choose-the-risk"},{"id":"training-loops-and-optimizers/optimizers-and-schedulers/s03-03-predict-the-checks"},{"id":"training-loops-and-optimizers/optimizers-and-schedulers/s04-04-fill-the-return"},{"id":"training-loops-and-optimizers/optimizers-and-schedulers/s05-05-fix-the-overtrust"},{"id":"training-loops-and-optimizers/optimizers-and-schedulers/s06-06-write-count-ready"},{"id":"training-loops-and-optimizers/optimizers-and-schedulers/s07-07-checkpoint"}]},{"slug":"checkpoints-and-reproducibility","steps":[{"id":"training-loops-and-optimizers/checkpoints-and-reproducibility/s01-01-intro"},{"id":"training-loops-and-optimizers/checkpoints-and-reproducibility/s02-02-choose-the-risk"},{"id":"training-loops-and-optimizers/checkpoints-and-reproducibility/s03-03-predict-the-checks"},{"id":"training-loops-and-optimizers/checkpoints-and-reproducibility/s04-04-fill-the-return"},{"id":"training-loops-and-optimizers/checkpoints-and-reproducibility/s05-05-fix-the-overtrust"},{"id":"training-loops-and-optimizers/checkpoints-and-reproducibility/s06-06-write-count-ready"},{"id":"training-loops-and-optimizers/checkpoints-and-reproducibility/s07-07-checkpoint"}]},{"slug":"mission-overfit-then-recover","steps":[{"id":"training-loops-and-optimizers/mission-overfit-then-recover/s01-01-intro"},{"id":"training-loops-and-optimizers/mission-overfit-then-recover/s02-02-choose-the-risk"},{"id":"training-loops-and-optimizers/mission-overfit-then-recover/s03-03-predict-the-checks"},{"id":"training-loops-and-optimizers/mission-overfit-then-recover/s04-04-fill-the-return"},{"id":"training-loops-and-optimizers/mission-overfit-then-recover/s05-05-fix-the-overtrust"},{"id":"training-loops-and-optimizers/mission-overfit-then-recover/s06-06-write-count-ready"},{"id":"training-loops-and-optimizers/mission-overfit-then-recover/s07-07-checkpoint"}]}]},{"slug":"deep-learning-architectures","lessons":[{"slug":"cnns-and-local-patterns","steps":[{"id":"deep-learning-architectures/cnns-and-local-patterns/s01-01-intro"},{"id":"deep-learning-architectures/cnns-and-local-patterns/s02-02-choose-the-risk"},{"id":"deep-learning-architectures/cnns-and-local-patterns/s03-03-predict-the-checks"},{"id":"deep-learning-architectures/cnns-and-local-patterns/s04-04-fill-the-return"},{"id":"deep-learning-architectures/cnns-and-local-patterns/s05-05-fix-the-overtrust"},{"id":"deep-learning-architectures/cnns-and-local-patterns/s06-06-write-count-ready"},{"id":"deep-learning-architectures/cnns-and-local-patterns/s07-07-checkpoint"}]},{"slug":"tokenizers-and-context-budget","steps":[{"id":"deep-learning-architectures/tokenizers-and-context-budget/s01-01-intro"},{"id":"deep-learning-architectures/tokenizers-and-context-budget/s02-02-choose-the-risk"},{"id":"deep-learning-architectures/tokenizers-and-context-budget/s03-03-predict-the-checks"},{"id":"deep-learning-architectures/tokenizers-and-context-budget/s04-04-fill-the-return"},{"id":"deep-learning-architectures/tokenizers-and-context-budget/s05-05-fix-the-overtrust"},{"id":"deep-learning-architectures/tokenizers-and-context-budget/s06-06-write-count-ready"},{"id":"deep-learning-architectures/tokenizers-and-context-budget/s07-07-checkpoint"}]},{"slug":"attention-and-transformer-blocks","steps":[{"id":"deep-learning-architectures/attention-and-transformer-blocks/s01-01-intro"},{"id":"deep-learning-architectures/attention-and-transformer-blocks/s02-02-choose-the-risk"},{"id":"deep-learning-architectures/attention-and-transformer-blocks/s03-03-predict-the-checks"},{"id":"deep-learning-architectures/attention-and-transformer-blocks/s04-04-fill-the-return"},{"id":"deep-learning-architectures/attention-and-transformer-blocks/s05-05-fix-the-overtrust"},{"id":"deep-learning-architectures/attention-and-transformer-blocks/s06-06-write-count-ready"},{"id":"deep-learning-architectures/attention-and-transformer-blocks/s07-07-checkpoint"}]},{"slug":"decoding-kv-cache-quantization","steps":[{"id":"deep-learning-architectures/decoding-kv-cache-quantization/s01-01-intro"},{"id":"deep-learning-architectures/decoding-kv-cache-quantization/s02-02-choose-the-risk"},{"id":"deep-learning-architectures/decoding-kv-cache-quantization/s03-03-predict-the-checks"},{"id":"deep-learning-architectures/decoding-kv-cache-quantization/s04-04-fill-the-return"},{"id":"deep-learning-architectures/decoding-kv-cache-quantization/s05-05-fix-the-overtrust"},{"id":"deep-learning-architectures/decoding-kv-cache-quantization/s06-06-write-count-ready"},{"id":"deep-learning-architectures/decoding-kv-cache-quantization/s07-07-checkpoint"}]},{"slug":"mission-architecture-tradeoff-note","steps":[{"id":"deep-learning-architectures/mission-architecture-tradeoff-note/s01-01-intro"},{"id":"deep-learning-architectures/mission-architecture-tradeoff-note/s02-02-choose-the-risk"},{"id":"deep-learning-architectures/mission-architecture-tradeoff-note/s03-03-predict-the-checks"},{"id":"deep-learning-architectures/mission-architecture-tradeoff-note/s04-04-fill-the-return"},{"id":"deep-learning-architectures/mission-architecture-tradeoff-note/s05-05-fix-the-overtrust"},{"id":"deep-learning-architectures/mission-architecture-tradeoff-note/s06-06-write-count-ready"},{"id":"deep-learning-architectures/mission-architecture-tradeoff-note/s07-07-checkpoint"}]}]},{"slug":"feature-experiments-registries","lessons":[{"slug":"feature-pipeline-contracts","steps":[{"id":"feature-experiments-registries/feature-pipeline-contracts/s01-01-intro"},{"id":"feature-experiments-registries/feature-pipeline-contracts/s02-02-choose-the-risk"},{"id":"feature-experiments-registries/feature-pipeline-contracts/s03-03-predict-the-checks"},{"id":"feature-experiments-registries/feature-pipeline-contracts/s04-04-fill-the-return"},{"id":"feature-experiments-registries/feature-pipeline-contracts/s05-05-fix-the-overtrust"},{"id":"feature-experiments-registries/feature-pipeline-contracts/s06-06-write-count-ready"},{"id":"feature-experiments-registries/feature-pipeline-contracts/s07-07-checkpoint"}]},{"slug":"train-inference-skew","steps":[{"id":"feature-experiments-registries/train-inference-skew/s01-01-intro"},{"id":"feature-experiments-registries/train-inference-skew/s02-02-choose-the-risk"},{"id":"feature-experiments-registries/train-inference-skew/s03-03-predict-the-checks"},{"id":"feature-experiments-registries/train-inference-skew/s04-04-fill-the-return"},{"id":"feature-experiments-registries/train-inference-skew/s05-05-fix-the-overtrust"},{"id":"feature-experiments-registries/train-inference-skew/s06-06-write-count-ready"},{"id":"feature-experiments-registries/train-inference-skew/s07-07-checkpoint"}]},{"slug":"experiment-tracker-lite","steps":[{"id":"feature-experiments-registries/experiment-tracker-lite/s01-01-intro"},{"id":"feature-experiments-registries/experiment-tracker-lite/s02-02-choose-the-risk"},{"id":"feature-experiments-registries/experiment-tracker-lite/s03-03-predict-the-checks"},{"id":"feature-experiments-registries/experiment-tracker-lite/s04-04-fill-the-return"},{"id":"feature-experiments-registries/experiment-tracker-lite/s05-05-fix-the-overtrust"},{"id":"feature-experiments-registries/experiment-tracker-lite/s06-06-write-count-ready"},{"id":"feature-experiments-registries/experiment-tracker-lite/s07-07-checkpoint"}]},{"slug":"model-registry-shape","steps":[{"id":"feature-experiments-registries/model-registry-shape/s01-01-intro"},{"id":"feature-experiments-registries/model-registry-shape/s02-02-choose-the-risk"},{"id":"feature-experiments-registries/model-registry-shape/s03-03-predict-the-checks"},{"id":"feature-experiments-registries/model-registry-shape/s04-04-fill-the-return"},{"id":"feature-experiments-registries/model-registry-shape/s05-05-fix-the-overtrust"},{"id":"feature-experiments-registries/model-registry-shape/s06-06-write-count-ready"},{"id":"feature-experiments-registries/model-registry-shape/s07-07-checkpoint"}]},{"slug":"mission-feature-pipeline-and-tracker","steps":[{"id":"feature-experiments-registries/mission-feature-pipeline-and-tracker/s01-01-intro"},{"id":"feature-experiments-registries/mission-feature-pipeline-and-tracker/s02-02-choose-the-risk"},{"id":"feature-experiments-registries/mission-feature-pipeline-and-tracker/s03-03-predict-the-checks"},{"id":"feature-experiments-registries/mission-feature-pipeline-and-tracker/s04-04-fill-the-return"},{"id":"feature-experiments-registries/mission-feature-pipeline-and-tracker/s05-05-fix-the-overtrust"},{"id":"feature-experiments-registries/mission-feature-pipeline-and-tracker/s06-06-write-count-ready"},{"id":"feature-experiments-registries/mission-feature-pipeline-and-tracker/s07-07-checkpoint"}]}]},{"slug":"model-serving-and-mlops","lessons":[{"slug":"fastapi-inference-shape","steps":[{"id":"model-serving-and-mlops/fastapi-inference-shape/s01-01-intro"},{"id":"model-serving-and-mlops/fastapi-inference-shape/s02-02-choose-the-risk"},{"id":"model-serving-and-mlops/fastapi-inference-shape/s03-03-predict-the-checks"},{"id":"model-serving-and-mlops/fastapi-inference-shape/s04-04-fill-the-return"},{"id":"model-serving-and-mlops/fastapi-inference-shape/s05-05-fix-the-overtrust"},{"id":"model-serving-and-mlops/fastapi-inference-shape/s06-06-write-count-ready"},{"id":"model-serving-and-mlops/fastapi-inference-shape/s07-07-checkpoint"}]},{"slug":"batch-vs-realtime-serving","steps":[{"id":"model-serving-and-mlops/batch-vs-realtime-serving/s01-01-intro"},{"id":"model-serving-and-mlops/batch-vs-realtime-serving/s02-02-choose-the-risk"},{"id":"model-serving-and-mlops/batch-vs-realtime-serving/s03-03-predict-the-checks"},{"id":"model-serving-and-mlops/batch-vs-realtime-serving/s04-04-fill-the-return"},{"id":"model-serving-and-mlops/batch-vs-realtime-serving/s05-05-fix-the-overtrust"},{"id":"model-serving-and-mlops/batch-vs-realtime-serving/s06-06-write-count-ready"},{"id":"model-serving-and-mlops/batch-vs-realtime-serving/s07-07-checkpoint"}]},{"slug":"docker-runtime-and-config","steps":[{"id":"model-serving-and-mlops/docker-runtime-and-config/s01-01-intro"},{"id":"model-serving-and-mlops/docker-runtime-and-config/s02-02-choose-the-risk"},{"id":"model-serving-and-mlops/docker-runtime-and-config/s03-03-predict-the-checks"},{"id":"model-serving-and-mlops/docker-runtime-and-config/s04-04-fill-the-return"},{"id":"model-serving-and-mlops/docker-runtime-and-config/s05-05-fix-the-overtrust"},{"id":"model-serving-and-mlops/docker-runtime-and-config/s06-06-write-count-ready"},{"id":"model-serving-and-mlops/docker-runtime-and-config/s07-07-checkpoint"}]},{"slug":"github-actions-validation-gates","steps":[{"id":"model-serving-and-mlops/github-actions-validation-gates/s01-01-intro"},{"id":"model-serving-and-mlops/github-actions-validation-gates/s02-02-choose-the-risk"},{"id":"model-serving-and-mlops/github-actions-validation-gates/s03-03-predict-the-checks"},{"id":"model-serving-and-mlops/github-actions-validation-gates/s04-04-fill-the-return"},{"id":"model-serving-and-mlops/github-actions-validation-gates/s05-05-fix-the-overtrust"},{"id":"model-serving-and-mlops/github-actions-validation-gates/s06-06-write-failing-checks"},{"id":"model-serving-and-mlops/github-actions-validation-gates/s07-07-checkpoint"}]},{"slug":"continuous-training-and-rollout","steps":[{"id":"model-serving-and-mlops/continuous-training-and-rollout/s01-01-intro"},{"id":"model-serving-and-mlops/continuous-training-and-rollout/s02-02-choose-the-risk"},{"id":"model-serving-and-mlops/continuous-training-and-rollout/s03-03-predict-the-checks"},{"id":"model-serving-and-mlops/continuous-training-and-rollout/s04-04-fill-the-return"},{"id":"model-serving-and-mlops/continuous-training-and-rollout/s05-05-fix-the-overtrust"},{"id":"model-serving-and-mlops/continuous-training-and-rollout/s06-06-write-count-ready"},{"id":"model-serving-and-mlops/continuous-training-and-rollout/s07-07-checkpoint"}]},{"slug":"mission-fastapi-model-server","steps":[{"id":"model-serving-and-mlops/mission-fastapi-model-server/s01-01-intro"},{"id":"model-serving-and-mlops/mission-fastapi-model-server/s02-02-choose-the-risk"},{"id":"model-serving-and-mlops/mission-fastapi-model-server/s03-03-predict-the-checks"},{"id":"model-serving-and-mlops/mission-fastapi-model-server/s04-04-fill-the-return"},{"id":"model-serving-and-mlops/mission-fastapi-model-server/s05-05-fix-the-overtrust"},{"id":"model-serving-and-mlops/mission-fastapi-model-server/s06-06-write-count-ready"},{"id":"model-serving-and-mlops/mission-fastapi-model-server/s07-07-checkpoint"}]}]},{"slug":"monitoring-cloud-portfolio","lessons":[{"slug":"structured-logs-and-alerts","steps":[{"id":"monitoring-cloud-portfolio/structured-logs-and-alerts/s01-01-intro"},{"id":"monitoring-cloud-portfolio/structured-logs-and-alerts/s02-02-choose-the-risk"},{"id":"monitoring-cloud-portfolio/structured-logs-and-alerts/s03-03-predict-the-checks"},{"id":"monitoring-cloud-portfolio/structured-logs-and-alerts/s04-04-fill-the-return"},{"id":"monitoring-cloud-portfolio/structured-logs-and-alerts/s05-05-fix-the-overtrust"},{"id":"monitoring-cloud-portfolio/structured-logs-and-alerts/s06-06-write-count-ready"},{"id":"monitoring-cloud-portfolio/structured-logs-and-alerts/s07-07-checkpoint"}]},{"slug":"data-and-concept-drift","steps":[{"id":"monitoring-cloud-portfolio/data-and-concept-drift/s01-01-intro"},{"id":"monitoring-cloud-portfolio/data-and-concept-drift/s02-02-choose-the-risk"},{"id":"monitoring-cloud-portfolio/data-and-concept-drift/s03-03-predict-the-checks"},{"id":"monitoring-cloud-portfolio/data-and-concept-drift/s04-04-fill-the-return"},{"id":"monitoring-cloud-portfolio/data-and-concept-drift/s05-05-fix-the-overtrust"},{"id":"monitoring-cloud-portfolio/data-and-concept-drift/s06-06-write-count-ready"},{"id":"monitoring-cloud-portfolio/data-and-concept-drift/s07-07-checkpoint"}]},{"slug":"retraining-triggers","steps":[{"id":"monitoring-cloud-portfolio/retraining-triggers/s01-01-intro"},{"id":"monitoring-cloud-portfolio/retraining-triggers/s02-02-choose-the-risk"},{"id":"monitoring-cloud-portfolio/retraining-triggers/s03-03-predict-the-checks"},{"id":"monitoring-cloud-portfolio/retraining-triggers/s04-04-fill-the-return"},{"id":"monitoring-cloud-portfolio/retraining-triggers/s05-05-fix-the-overtrust"},{"id":"monitoring-cloud-portfolio/retraining-triggers/s06-06-write-count-ready"},{"id":"monitoring-cloud-portfolio/retraining-triggers/s07-07-checkpoint"}]},{"slug":"cloud-gpu-kubernetes-cost","steps":[{"id":"monitoring-cloud-portfolio/cloud-gpu-kubernetes-cost/s01-01-intro"},{"id":"monitoring-cloud-portfolio/cloud-gpu-kubernetes-cost/s02-02-choose-the-risk"},{"id":"monitoring-cloud-portfolio/cloud-gpu-kubernetes-cost/s03-03-predict-the-checks"},{"id":"monitoring-cloud-portfolio/cloud-gpu-kubernetes-cost/s04-04-fill-the-return"},{"id":"monitoring-cloud-portfolio/cloud-gpu-kubernetes-cost/s05-05-fix-the-overtrust"},{"id":"monitoring-cloud-portfolio/cloud-gpu-kubernetes-cost/s06-06-write-count-ready"},{"id":"monitoring-cloud-portfolio/cloud-gpu-kubernetes-cost/s07-07-checkpoint"}]},{"slug":"portfolio-architecture-docs","steps":[{"id":"monitoring-cloud-portfolio/portfolio-architecture-docs/s01-01-intro"},{"id":"monitoring-cloud-portfolio/portfolio-architecture-docs/s02-02-choose-the-risk"},{"id":"monitoring-cloud-portfolio/portfolio-architecture-docs/s03-03-predict-the-checks"},{"id":"monitoring-cloud-portfolio/portfolio-architecture-docs/s04-04-fill-the-return"},{"id":"monitoring-cloud-portfolio/portfolio-architecture-docs/s05-05-fix-the-overtrust"},{"id":"monitoring-cloud-portfolio/portfolio-architecture-docs/s06-06-write-count-ready"},{"id":"monitoring-cloud-portfolio/portfolio-architecture-docs/s07-07-checkpoint"}]},{"slug":"mission-final-portfolio-ml-system","steps":[{"id":"monitoring-cloud-portfolio/mission-final-portfolio-ml-system/s01-01-intro"},{"id":"monitoring-cloud-portfolio/mission-final-portfolio-ml-system/s02-02-choose-the-risk"},{"id":"monitoring-cloud-portfolio/mission-final-portfolio-ml-system/s03-03-predict-the-checks"},{"id":"monitoring-cloud-portfolio/mission-final-portfolio-ml-system/s04-04-fill-the-return"},{"id":"monitoring-cloud-portfolio/mission-final-portfolio-ml-system/s05-05-fix-the-overtrust"},{"id":"monitoring-cloud-portfolio/mission-final-portfolio-ml-system/s06-06-write-decide"},{"id":"monitoring-cloud-portfolio/mission-final-portfolio-ml-system/s07-07-checkpoint"}]}]},{"slug":"graphic-design-studio","lessons":[{"slug":"prompting-like-an-art-director","steps":[{"id":"graphic-design-studio/prompting-like-an-art-director/s01-01-the-prompt-is-a-creative-brief"},{"id":"graphic-design-studio/prompting-like-an-art-director/s02-02-style-language"},{"id":"graphic-design-studio/prompting-like-an-art-director/s03-03-which-tool-for-the-headline"},{"id":"graphic-design-studio/prompting-like-an-art-director/s04-04-predict-the-scaffold"},{"id":"graphic-design-studio/prompting-like-an-art-director/s05-05-negative-space-and-the-iteration-loop"},{"id":"graphic-design-studio/prompting-like-an-art-director/s06-06-fix-the-mood-word-prompt"},{"id":"graphic-design-studio/prompting-like-an-art-director/s07-07-write-prompt-linter"},{"id":"graphic-design-studio/prompting-like-an-art-director/s08-08-checkpoint"}]},{"slug":"the-design-kit","steps":[{"id":"graphic-design-studio/the-design-kit/s01-01-the-brand-bible-as-data"},{"id":"graphic-design-studio/the-design-kit/s02-02-fill-the-palette-line"},{"id":"graphic-design-studio/the-design-kit/s03-03-banned-looks"},{"id":"graphic-design-studio/the-design-kit/s04-04-predict-the-negatives"},{"id":"graphic-design-studio/the-design-kit/s05-05-which-field-failed"},{"id":"graphic-design-studio/the-design-kit/s06-06-fix-the-crossed-kit"},{"id":"graphic-design-studio/the-design-kit/s07-07-write-contrast-check"},{"id":"graphic-design-studio/the-design-kit/s08-08-tokens-for-the-interface"},{"id":"graphic-design-studio/the-design-kit/s09-09-write-token-audit"},{"id":"graphic-design-studio/the-design-kit/s10-10-checkpoint"}]},{"slug":"fifty-assets-one-brand","steps":[{"id":"graphic-design-studio/fifty-assets-one-brand/s01-01-the-consistency-problem"},{"id":"graphic-design-studio/fifty-assets-one-brand/s02-02-seeds-the-same-dice-twice"},{"id":"graphic-design-studio/fifty-assets-one-brand/s03-03-why-does-the-mascot-drift"},{"id":"graphic-design-studio/fifty-assets-one-brand/s04-04-predict-the-batch-plan"},{"id":"graphic-design-studio/fifty-assets-one-brand/s05-05-the-qa-filter"},{"id":"graphic-design-studio/fifty-assets-one-brand/s06-06-defend-the-pick"},{"id":"graphic-design-studio/fifty-assets-one-brand/s07-07-fix-the-qa-threshold"},{"id":"graphic-design-studio/fifty-assets-one-brand/s08-08-write-palette-distance"},{"id":"graphic-design-studio/fifty-assets-one-brand/s09-09-checkpoint"}]}]},{"slug":"campaign-studio","lessons":[{"slug":"voice-pack-as-data","steps":[{"id":"campaign-studio/voice-pack-as-data/s01-01-the-campaign-and-the-gate"},{"id":"campaign-studio/voice-pack-as-data/s02-02-lint-the-draft"},{"id":"campaign-studio/voice-pack-as-data/s03-03-predict-the-violations"},{"id":"campaign-studio/voice-pack-as-data/s04-04-testable-or-mood"},{"id":"campaign-studio/voice-pack-as-data/s05-05-fill-the-linter"},{"id":"campaign-studio/voice-pack-as-data/s06-06-variants-as-records"},{"id":"campaign-studio/voice-pack-as-data/s07-07-write-lint-copy"},{"id":"campaign-studio/voice-pack-as-data/s08-08-checkpoint"}]},{"slug":"batch-plan-and-calendar","steps":[{"id":"campaign-studio/batch-plan-and-calendar/s01-01-slots-before-prompts"},{"id":"campaign-studio/batch-plan-and-calendar/s02-02-which-field-is-missing"},{"id":"campaign-studio/batch-plan-and-calendar/s03-03-write-batch-plan"},{"id":"campaign-studio/batch-plan-and-calendar/s04-04-the-calendar-is-data"},{"id":"campaign-studio/batch-plan-and-calendar/s05-05-predict-the-queue"},{"id":"campaign-studio/batch-plan-and-calendar/s06-06-fix-the-gate"},{"id":"campaign-studio/batch-plan-and-calendar/s07-07-checkpoint"}]},{"slug":"the-numbers-pass","steps":[{"id":"campaign-studio/the-numbers-pass/s01-01-a-report-is-a-draft-over-data"},{"id":"campaign-studio/the-numbers-pass/s02-02-predict-the-verdict"},{"id":"campaign-studio/the-numbers-pass/s03-03-write-verify-numbers"},{"id":"campaign-studio/the-numbers-pass/s04-04-denominators-and-the-ftc"},{"id":"campaign-studio/the-numbers-pass/s05-05-what-may-not-ship"},{"id":"campaign-studio/the-numbers-pass/s06-06-fill-the-policy-router"},{"id":"campaign-studio/the-numbers-pass/s07-07-checkpoint"}]}]},{"slug":"support-studio","lessons":[{"slug":"the-policy-pack","steps":[{"id":"support-studio/the-policy-pack/s01-01-the-reply-that-binds-the-company"},{"id":"support-studio/the-policy-pack/s02-02-the-pack-as-data"},{"id":"support-studio/the-policy-pack/s03-03-spot-the-banned-promise"},{"id":"support-studio/the-policy-pack/s04-04-predict-the-lint"},{"id":"support-studio/the-policy-pack/s05-05-fix-the-stale-citation"},{"id":"support-studio/the-policy-pack/s06-06-the-review-loop-evidence"},{"id":"support-studio/the-policy-pack/s07-07-write-lint-draft"},{"id":"support-studio/the-policy-pack/s08-08-checkpoint"}]},{"slug":"golden-evals-earn-autonomy","steps":[{"id":"support-studio/golden-evals-earn-autonomy/s01-01-the-klarna-arc"},{"id":"support-studio/golden-evals-earn-autonomy/s02-02-a-macro-is-three-things"},{"id":"support-studio/golden-evals-earn-autonomy/s03-03-inside-the-lane"},{"id":"support-studio/golden-evals-earn-autonomy/s04-04-predict-the-eval-run"},{"id":"support-studio/golden-evals-earn-autonomy/s05-05-fill-the-promotion-rule"},{"id":"support-studio/golden-evals-earn-autonomy/s06-06-write-run-golden-evals"},{"id":"support-studio/golden-evals-earn-autonomy/s07-07-checkpoint"}]},{"slug":"the-escalation-boundary","steps":[{"id":"support-studio/the-escalation-boundary/s01-01-drafting-is-not-spending"},{"id":"support-studio/the-escalation-boundary/s02-02-triggers-as-conditions"},{"id":"support-studio/the-escalation-boundary/s03-03-route-this-ticket"},{"id":"support-studio/the-escalation-boundary/s04-04-predict-the-routing"},{"id":"support-studio/the-escalation-boundary/s05-05-fix-the-refund-hole"},{"id":"support-studio/the-escalation-boundary/s06-06-disclosure-and-the-kill-switch"},{"id":"support-studio/the-escalation-boundary/s07-07-write-route-ticket"},{"id":"support-studio/the-escalation-boundary/s08-08-checkpoint"}]}]},{"slug":"copy-studio","lessons":[{"slug":"the-voice-fingerprint","steps":[{"id":"copy-studio/the-voice-fingerprint/s01-01-the-client-you-inherit"},{"id":"copy-studio/the-voice-fingerprint/s02-02-the-fingerprint"},{"id":"copy-studio/the-voice-fingerprint/s03-03-predict-the-ceiling"},{"id":"copy-studio/the-voice-fingerprint/s04-04-the-samples-say-otherwise"},{"id":"copy-studio/the-voice-fingerprint/s05-05-fill-derive-the-rules"},{"id":"copy-studio/the-voice-fingerprint/s06-06-the-pack-with-provenance"},{"id":"copy-studio/the-voice-fingerprint/s07-07-write-fingerprint"},{"id":"copy-studio/the-voice-fingerprint/s08-08-checkpoint"}]},{"slug":"variants-that-hold-the-line","steps":[{"id":"copy-studio/variants-that-hold-the-line/s01-01-twelve-by-thursday"},{"id":"copy-studio/variants-that-hold-the-line/s02-02-the-drift-problem"},{"id":"copy-studio/variants-that-hold-the-line/s03-03-predict-the-drift-report"},{"id":"copy-studio/variants-that-hold-the-line/s04-04-which-subject-line-ships"},{"id":"copy-studio/variants-that-hold-the-line/s05-05-fix-the-channel-check"},{"id":"copy-studio/variants-that-hold-the-line/s06-06-the-kill-log"},{"id":"copy-studio/variants-that-hold-the-line/s07-07-write-voice-gate"},{"id":"copy-studio/variants-that-hold-the-line/s08-08-checkpoint"}]},{"slug":"the-claim-check","steps":[{"id":"copy-studio/the-claim-check/s01-01-forty-one-of-seventy-seven"},{"id":"copy-studio/the-claim-check/s02-02-what-counts-as-checkable"},{"id":"copy-studio/the-claim-check/s03-03-predict-the-claim-list"},{"id":"copy-studio/the-claim-check/s04-04-what-closes-a-row"},{"id":"copy-studio/the-claim-check/s05-05-fill-the-ship-decision"},{"id":"copy-studio/the-claim-check/s06-06-the-corrections-log"},{"id":"copy-studio/the-claim-check/s07-07-write-ship-gate"},{"id":"copy-studio/the-claim-check/s08-08-checkpoint"}]}]},{"slug":"analytics-studio","lessons":[{"slug":"the-cleaning-log","steps":[{"id":"analytics-studio/the-cleaning-log/s01-01-where-did-those-rows-go"},{"id":"analytics-studio/the-cleaning-log/s02-02-the-log-as-data"},{"id":"analytics-studio/the-cleaning-log/s03-03-refuse-the-silent-step"},{"id":"analytics-studio/the-cleaning-log/s04-04-predict-the-receipts"},{"id":"analytics-studio/the-cleaning-log/s05-05-fill-the-null-decision"},{"id":"analytics-studio/the-cleaning-log/s06-06-fix-the-vanishing-rows"},{"id":"analytics-studio/the-cleaning-log/s07-07-write-the-null-ledger"},{"id":"analytics-studio/the-cleaning-log/s08-08-checkpoint"}]},{"slug":"every-number-has-an-address","steps":[{"id":"analytics-studio/every-number-has-an-address/s01-01-the-plausible-wrong-number"},{"id":"analytics-studio/every-number-has-an-address/s02-02-sample-first-then-full"},{"id":"analytics-studio/every-number-has-an-address/s03-03-which-check-catches-it"},{"id":"analytics-studio/every-number-has-an-address/s04-04-predict-the-fan-out"},{"id":"analytics-studio/every-number-has-an-address/s05-05-fill-the-trace"},{"id":"analytics-studio/every-number-has-an-address/s06-06-write-audit-the-memo"},{"id":"analytics-studio/every-number-has-an-address/s07-07-checkpoint"}]},{"slug":"challenge-then-rerun","steps":[{"id":"analytics-studio/challenge-then-rerun/s01-01-the-confident-recommendation"},{"id":"analytics-studio/challenge-then-rerun/s02-02-the-triad-as-a-checklist"},{"id":"analytics-studio/challenge-then-rerun/s03-03-name-the-leg"},{"id":"analytics-studio/challenge-then-rerun/s04-04-predict-the-rerun"},{"id":"analytics-studio/challenge-then-rerun/s05-05-fix-the-drifting-memo"},{"id":"analytics-studio/challenge-then-rerun/s06-06-write-score-the-challenge"},{"id":"analytics-studio/challenge-then-rerun/s07-07-checkpoint"}]}]},{"slug":"delivery-studio","lessons":[{"slug":"the-spec-is-the-build","steps":[{"id":"delivery-studio/the-spec-is-the-build/s01-01-the-clarifying-question-is-gone"},{"id":"delivery-studio/the-spec-is-the-build/s02-02-the-ticket-as-data"},{"id":"delivery-studio/the-spec-is-the-build/s03-03-spot-the-untestable-check"},{"id":"delivery-studio/the-spec-is-the-build/s04-04-predict-the-spec-lint"},{"id":"delivery-studio/the-spec-is-the-build/s05-05-fill-the-scope-fence"},{"id":"delivery-studio/the-spec-is-the-build/s06-06-inside-or-outside-the-frontier"},{"id":"delivery-studio/the-spec-is-the-build/s07-07-write-lint-spec"},{"id":"delivery-studio/the-spec-is-the-build/s08-08-checkpoint"}]},{"slug":"acceptance-before-the-build","steps":[{"id":"delivery-studio/acceptance-before-the-build/s01-01-the-ninety-seven-thousand-dollar-skip"},{"id":"delivery-studio/acceptance-before-the-build/s02-02-evidence-against-the-checks"},{"id":"delivery-studio/acceptance-before-the-build/s03-03-which-check-catches-it"},{"id":"delivery-studio/acceptance-before-the-build/s04-04-fix-the-vibes-review"},{"id":"delivery-studio/acceptance-before-the-build/s05-05-predict-the-review-run"},{"id":"delivery-studio/acceptance-before-the-build/s06-06-rework-is-a-list-not-a-feeling"},{"id":"delivery-studio/acceptance-before-the-build/s07-07-write-review-deliverable"},{"id":"delivery-studio/acceptance-before-the-build/s08-08-checkpoint"}]},{"slug":"status-from-artifacts","steps":[{"id":"delivery-studio/status-from-artifacts/s01-01-watermelon-status"},{"id":"delivery-studio/status-from-artifacts/s02-02-derive-the-rag"},{"id":"delivery-studio/status-from-artifacts/s03-03-spot-the-artifact"},{"id":"delivery-studio/status-from-artifacts/s04-04-fill-the-worst-of"},{"id":"delivery-studio/status-from-artifacts/s05-05-predict-the-rollup"},{"id":"delivery-studio/status-from-artifacts/s06-06-the-not-ready-call"},{"id":"delivery-studio/status-from-artifacts/s07-07-write-readiness-gate"},{"id":"delivery-studio/status-from-artifacts/s08-08-checkpoint"}]},{"slug":"the-hours-saved-receipt","steps":[{"id":"delivery-studio/the-hours-saved-receipt/s01-01-the-token-chart-is-not-a-receipt"},{"id":"delivery-studio/the-hours-saved-receipt/s02-02-the-receipt-as-data"},{"id":"delivery-studio/the-hours-saved-receipt/s03-03-which-line-survives-staff-meeting"},{"id":"delivery-studio/the-hours-saved-receipt/s04-04-fix-the-vanity-chart"},{"id":"delivery-studio/the-hours-saved-receipt/s05-05-predict-the-receipt-run"},{"id":"delivery-studio/the-hours-saved-receipt/s06-06-only-accepted-ships-count"},{"id":"delivery-studio/the-hours-saved-receipt/s07-07-write-hours-receipt"},{"id":"delivery-studio/the-hours-saved-receipt/s08-08-checkpoint"}]}]},{"slug":"people-studio","lessons":[{"slug":"the-data-firewall","steps":[{"id":"people-studio/the-data-firewall/s01-01-the-rule-that-cannot-live-in-memory"},{"id":"people-studio/the-data-firewall/s02-02-the-firewall-as-data"},{"id":"people-studio/the-data-firewall/s03-03-which-payload-passes"},{"id":"people-studio/the-data-firewall/s04-04-predict-the-scan"},{"id":"people-studio/the-data-firewall/s05-05-fix-the-leaky-gate"},{"id":"people-studio/the-data-firewall/s06-06-employee-relations-takes-nothing"},{"id":"people-studio/the-data-firewall/s07-07-write-prompt-gate"},{"id":"people-studio/the-data-firewall/s08-08-checkpoint"}]},{"slug":"briefs-with-receipts","steps":[{"id":"people-studio/briefs-with-receipts/s01-01-the-most-automated-desk"},{"id":"people-studio/briefs-with-receipts/s02-02-a-claim-with-a-receipt"},{"id":"people-studio/briefs-with-receipts/s03-03-sourced-or-inference"},{"id":"people-studio/briefs-with-receipts/s04-04-predict-the-receipt-audit"},{"id":"people-studio/briefs-with-receipts/s05-05-fill-the-lookup"},{"id":"people-studio/briefs-with-receipts/s06-06-the-screening-line"},{"id":"people-studio/briefs-with-receipts/s07-07-write-audit-brief"},{"id":"people-studio/briefs-with-receipts/s08-08-checkpoint"}]},{"slug":"the-paper-trail","steps":[{"id":"people-studio/the-paper-trail/s01-01-policy-is-legal-surface"},{"id":"people-studio/the-paper-trail/s02-02-the-boundary-as-a-state-machine"},{"id":"people-studio/the-paper-trail/s03-03-who-signs-off"},{"id":"people-studio/the-paper-trail/s04-04-predict-the-version-log"},{"id":"people-studio/the-paper-trail/s05-05-fix-the-shortcut"},{"id":"people-studio/the-paper-trail/s06-06-the-evidence-trail"},{"id":"people-studio/the-paper-trail/s07-07-write-decision-record"},{"id":"people-studio/the-paper-trail/s08-08-checkpoint"}]}]},{"slug":"ops-studio","lessons":[{"slug":"the-sop-is-data","steps":[{"id":"ops-studio/the-sop-is-data/s01-01-the-two-weeks-notice-problem"},{"id":"ops-studio/the-sop-is-data/s02-02-the-sop-as-data"},{"id":"ops-studio/the-sop-is-data/s03-03-spot-the-invented-step"},{"id":"ops-studio/the-sop-is-data/s04-04-fill-the-sop-lint"},{"id":"ops-studio/the-sop-is-data/s05-05-predict-the-diff"},{"id":"ops-studio/the-sop-is-data/s06-06-the-diff-is-the-change-control"},{"id":"ops-studio/the-sop-is-data/s07-07-write-lint-sop"},{"id":"ops-studio/the-sop-is-data/s08-08-checkpoint"}]},{"slug":"auto-run-or-named-approval","steps":[{"id":"ops-studio/auto-run-or-named-approval/s01-01-the-checklist-that-lied"},{"id":"ops-studio/auto-run-or-named-approval/s02-02-the-schedule-is-data"},{"id":"ops-studio/auto-run-or-named-approval/s03-03-which-item-may-auto-run"},{"id":"ops-studio/auto-run-or-named-approval/s04-04-fix-the-silent-auto-complete"},{"id":"ops-studio/auto-run-or-named-approval/s05-05-predict-the-exception-queue"},{"id":"ops-studio/auto-run-or-named-approval/s06-06-exceptions-are-a-queue-not-a-shrug"},{"id":"ops-studio/auto-run-or-named-approval/s07-07-write-run-checklist"},{"id":"ops-studio/auto-run-or-named-approval/s08-08-checkpoint"}]},{"slug":"numbers-with-receipts","steps":[{"id":"ops-studio/numbers-with-receipts/s01-01-the-number-that-moves-money"},{"id":"ops-studio/numbers-with-receipts/s02-02-recompute-dont-trust"},{"id":"ops-studio/numbers-with-receipts/s03-03-which-claim-has-no-receipt"},{"id":"ops-studio/numbers-with-receipts/s04-04-predict-the-verification"},{"id":"ops-studio/numbers-with-receipts/s05-05-fill-the-receipt-check"},{"id":"ops-studio/numbers-with-receipts/s06-06-the-anomaly-is-a-question"},{"id":"ops-studio/numbers-with-receipts/s07-07-write-verify-report"},{"id":"ops-studio/numbers-with-receipts/s08-08-checkpoint"}]},{"slug":"the-pii-proxy","steps":[{"id":"ops-studio/the-pii-proxy/s01-01-the-ticket-that-left-the-building"},{"id":"ops-studio/the-pii-proxy/s02-02-mask-then-unmask"},{"id":"ops-studio/the-pii-proxy/s03-03-which-payload-may-leave"},{"id":"ops-studio/the-pii-proxy/s04-04-fill-the-leftover-check"},{"id":"ops-studio/the-pii-proxy/s05-05-predict-the-two-sides"},{"id":"ops-studio/the-pii-proxy/s06-06-unmask-is-a-named-human-act"},{"id":"ops-studio/the-pii-proxy/s07-07-write-the-proxy"},{"id":"ops-studio/the-pii-proxy/s08-08-checkpoint"}]}]},{"slug":"legal-studio","lessons":[{"slug":"the-cite-check-gate","steps":[{"id":"legal-studio/the-cite-check-gate/s01-01-the-brief-that-reads-perfectly"},{"id":"legal-studio/the-cite-check-gate/s02-02-three-verdicts-as-data"},{"id":"legal-studio/the-cite-check-gate/s03-03-which-cite-needs-no-check"},{"id":"legal-studio/the-cite-check-gate/s04-04-predict-the-verification-run"},{"id":"legal-studio/the-cite-check-gate/s05-05-fix-the-verifier-that-asks-again"},{"id":"legal-studio/the-cite-check-gate/s06-06-write-verify-authorities"},{"id":"legal-studio/the-cite-check-gate/s07-07-checkpoint"}]},{"slug":"clause-extraction-with-pinpoints","steps":[{"id":"legal-studio/clause-extraction-with-pinpoints/s01-01-a-claim-without-a-pinpoint-is-a-rumor"},{"id":"legal-studio/clause-extraction-with-pinpoints/s02-02-the-playbook-as-data"},{"id":"legal-studio/clause-extraction-with-pinpoints/s03-03-which-row-is-unusable"},{"id":"legal-studio/clause-extraction-with-pinpoints/s04-04-predict-the-triage"},{"id":"legal-studio/clause-extraction-with-pinpoints/s05-05-fill-the-walk-away-route"},{"id":"legal-studio/clause-extraction-with-pinpoints/s06-06-write-triage-extraction"},{"id":"legal-studio/clause-extraction-with-pinpoints/s07-07-checkpoint"}]},{"slug":"privilege-rules-and-the-review-log","steps":[{"id":"legal-studio/privilege-rules-and-the-review-log/s01-01-privilege-is-a-routing-question"},{"id":"legal-studio/privilege-rules-and-the-review-log/s02-02-the-routing-table"},{"id":"legal-studio/privilege-rules-and-the-review-log/s03-03-which-request-is-the-waiver-risk"},{"id":"legal-studio/privilege-rules-and-the-review-log/s04-04-predict-the-router"},{"id":"legal-studio/privilege-rules-and-the-review-log/s05-05-fix-the-privilege-hole"},{"id":"legal-studio/privilege-rules-and-the-review-log/s06-06-the-log-that-survives-a-motion"},{"id":"legal-studio/privilege-rules-and-the-review-log/s07-07-write-log-ready"},{"id":"legal-studio/privilege-rules-and-the-review-log/s08-08-checkpoint"}]}]},{"slug":"agent-studio","lessons":[{"slug":"the-tool-contract","steps":[{"id":"agent-studio/the-tool-contract/s01-01-the-feature-you-ship-today"},{"id":"agent-studio/the-tool-contract/s02-02-the-schema-is-the-blast-radius"},{"id":"agent-studio/the-tool-contract/s03-03-spot-the-loose-tool"},{"id":"agent-studio/the-tool-contract/s04-04-predict-the-validation"},{"id":"agent-studio/the-tool-contract/s05-05-fix-the-yolo-rerun"},{"id":"agent-studio/the-tool-contract/s06-06-write-validate-call"},{"id":"agent-studio/the-tool-contract/s07-07-checkpoint"}]},{"slug":"the-loop-with-a-meter","steps":[{"id":"agent-studio/the-loop-with-a-meter/s01-01-a-loop-that-cannot-stop-is-an-invoice"},{"id":"agent-studio/the-loop-with-a-meter/s02-02-caps-are-part-of-the-loop"},{"id":"agent-studio/the-loop-with-a-meter/s03-03-why-did-it-stop"},{"id":"agent-studio/the-loop-with-a-meter/s04-04-predict-the-stop-reason"},{"id":"agent-studio/the-loop-with-a-meter/s05-05-fill-the-budget-check"},{"id":"agent-studio/the-loop-with-a-meter/s06-06-the-trace-is-the-receipt"},{"id":"agent-studio/the-loop-with-a-meter/s07-07-write-run-loop"},{"id":"agent-studio/the-loop-with-a-meter/s08-08-checkpoint"}]},{"slug":"evals-before-it-works","steps":[{"id":"agent-studio/evals-before-it-works/s01-01-green-before-it-runs"},{"id":"agent-studio/evals-before-it-works/s02-02-a-golden-case-is-a-past-incident"},{"id":"agent-studio/evals-before-it-works/s03-03-which-case-catches-it"},{"id":"agent-studio/evals-before-it-works/s04-04-predict-the-eval-run"},{"id":"agent-studio/evals-before-it-works/s05-05-fix-the-router-to-green"},{"id":"agent-studio/evals-before-it-works/s06-06-the-ratchet-entry"},{"id":"agent-studio/evals-before-it-works/s07-07-write-lint-the-ratchet"},{"id":"agent-studio/evals-before-it-works/s08-08-checkpoint"}]}]}]},"detail":{"number":26,"slug":"agent-harnesses","title":"agent harnesses — the layer between you and the raw api","blurb":"claude code, cursor, aider, codex cli — they're all the same four layers wrapped around the same model api. learn what those layers are, what each adds, and what you'd build yourself if you had to. when the harness changes the world, the rollback lives in the repo — a runbook a junior can execute at 3am.","overview":"$27","status":"live","lessons":[{"slug":"project-workspaces-not-product-names","title":"Project workspaces, not product names","estMinutes":8,"prerequisites":[],"status":"live","steps":[{"type":"read","id":"agent-harnesses/project-workspaces-not-product-names/s01-01-intro","xp":2,"hint":[],"personalize":false,"phase":"warmup","estSeconds":300,"concept":"project-workspaces-not-product-names","body":"$28","cta":"Got it","runnable":true}],"xpTotal":2},{"slug":"what-a-harness-is","title":"What a harness is — the four layers under every coding agent","estMinutes":12,"prerequisites":[],"status":"live","steps":[{"type":"read","id":"agent-harnesses/what-a-harness-is/s01-01-intro","xp":1,"hint":[],"personalize":false,"phase":"warmup","estSeconds":130,"concept":"harness-vs-raw-call","body":"$29","cta":"Got it","code":"$2a","runnable":true},{"type":"mc","id":"agent-harnesses/what-a-harness-is/s02-02-which-is-a-harness","xp":2,"hint":[{"level":1,"body":"The discriminator is layer 4: tool dispatch. Can the system DO something (edit a file, run a command, search the web) on the model's behalf? If yes, harness. If no (just chat), wrapper.","cost":0}],"personalize":false,"phase":"warmup","estSeconds":55,"concept":"harness-vs-wrapper","prompt":"A \"harness\" wraps the model API with at least: input prep, model\ncall, output parsing, AND tool dispatch (the model can change the\nworld, not just describe it). Which TWO of the systems above are\nharnesses?\n","options":[{"id":"b_and_d","label":"B (Cursor) and D (Aider)"},{"id":"all_four","label":"All four — anything that calls a model is a harness","explain":"A and C are wrappers — they call the model and render output, but the model can't change anything. No tool dispatch = not a harness."},{"id":"a_and_b","label":"A and B","explain":"A is just a script that calls the API. No tools, no input prep beyond a hardcoded prompt — it's a wrapper, not a harness."},{"id":"c_and_d","label":"C and D","explain":"C is a chat UI. The model talks; nothing changes outside the chat window. No tool dispatch."}],"answerIds":["b_and_d"],"shuffle":false,"code":"systems = {\n \"A\": \"A Python script that calls anthropic.messages.create with a hardcoded prompt and prints the result.\",\n \"B\": \"Cursor — reads open files, runs edits, applies diffs, has tools.\",\n \"C\": \"A web chat UI that sends user input to gpt-4o and renders the response.\",\n \"D\": \"Aider — gathers repo context, calls model, applies file edits, integrates with git.\",\n}\nfor k, v in systems.items():\n print(f\"{k}: {v}\")\n","runnable":true},{"type":"read","id":"agent-harnesses/what-a-harness-is/s03-03-the-four-layers","xp":2,"hint":[],"personalize":false,"phase":"build","estSeconds":110,"concept":"four-harness-layers","body":"$2b","cta":"Got it","code":"# the four layers, named and ordered.\n\nLAYERS = [\n \"1. input prep — load config, gather context, build messages\",\n \"2. model call — messages.create with retries, cache, routing\",\n \"3. output parsing — separate text from tool_use, accumulate\",\n \"4. tool dispatch — run requested tools, append results, loop\",\n]\nfor layer in LAYERS:\n print(layer)\n","runnable":true},{"type":"predict","id":"agent-harnesses/what-a-harness-is/s04-04-predict-the-layer","xp":3,"hint":[{"level":1,"body":"Layer 1 (input prep): `load_claude_md` = 1. Layer 2 (model call + retries): `messages.create` and `with_retries` = 2. Layer 3 (output parsing): `for block in response.content` = 1. Layer 4 (tool dispatch): `TOOLS[name](**args)` = 1.","cost":0}],"personalize":false,"phase":"build","estSeconds":80,"concept":"classify-harness-code-by-layer","code":"# five lines from a real harness. each belongs to one layer.\n\nsnippets = {\n \"load_claude_md(root)\": 1,\n \"client.messages.create(...)\": 2,\n \"for block in response.content:\": 3,\n \"TOOLS[name](**args)\": 4,\n \"with_retries(call, max_attempts=3)\": 2,\n}\n\nlayer_counts = [0, 0, 0, 0, 0] # index 1..4 used\nfor code, layer in snippets.items():\n layer_counts[layer] += 1\n\nfor i in range(1, 5):\n print(f\"layer {i}: {layer_counts[i]}\")\n","prompt":"Read the editor. Five snippets, classified into the four layers.\nThe script counts how many snippets land in each layer. What\ndoes it print?\n","grader":{"kind":"stdout-equality","expected":"layer 1: 1\nlayer 2: 2\nlayer 3: 1\nlayer 4: 1\n","normalize":"collapse-trailing-newline"}},{"type":"fill","id":"agent-harnesses/what-a-harness-is/s05-05-fill-the-dispatch","xp":3,"hint":[{"level":1,"body":"Two pieces: registry lookup `TOOLS[name]`, then call with `**input` to unpack the dict as keyword arguments.","cost":0},{"level":2,"body":"`TOOLS[tool_use[\"name\"]](**tool_use[\"input\"])` — the canonical layer-4 dispatch.","cost":0}],"personalize":false,"phase":"build","estSeconds":65,"concept":"tool-registry-dispatch","prompt":"The harness has a tool registry (a dict) and a `tool_use` block\nfrom the model. Fill in the dispatch line: look up the tool by\nname and call it with the input dict unpacked.\n\nExpected output:\n```\nresults for tokyo\n```\n","code":"TOOLS = {\n \"search\": lambda q: f\"results for {q}\",\n \"read\": lambda path: f\"\",\n}\n\ntool_use = {\"name\": \"search\", \"input\": {\"q\": \"tokyo\"}}\n\nresult = ___\nprint(result)\n","blanks":[{"id":"dispatch","accept":["TOOLS[tool_use[\"name\"]](**tool_use[\"input\"])","TOOLS[tool_use['name']](**tool_use['input'])"],"caseSensitive":true,"normalize":"trim"}]},{"type":"fix","id":"agent-harnesses/what-a-harness-is/s06-06-fix-the-no-retry","xp":4,"hint":[{"level":1,"body":"Wrap the call in a loop `for attempt in range(max_attempts)`. Try, except TransientError — if not the last attempt, continue. Else re-raise. Else (success) return result.","cost":0},{"level":2,"body":"Replace the body of `call_with_retries`:\n\n```python\nfor attempt in range(max_attempts):\n try:\n return fn()\n except TransientError:\n if attempt == max_attempts - 1:\n raise\n```\n","cost":0}],"personalize":false,"phase":"build","estSeconds":100,"concept":"retries-around-model-call","brokenCode":"call_count = {\"n\": 0}\n\nclass TransientError(Exception):\n transient = True\n\ndef flaky_call():\n call_count[\"n\"] += 1\n if call_count[\"n\"] < 3:\n raise TransientError(\"503 service unavailable\")\n return \"succeeded on attempt 3\"\n\ndef call_with_retries(fn, max_attempts=3):\n # bug: no retry. one attempt, raises on first failure.\n return fn()\n\nprint(call_with_retries(flaky_call))\n","prompt":"The harness's layer-2 code calls the model exactly once. If the\ncall hits a transient 429 (rate limit) or 503 (service\nunavailable), it raises and the user sees a crash. Production\nharnesses retry transient failures with exponential backoff.\n\nFix `call_with_retries(fn, max_attempts=3)` to retry up to 3\ntimes on transient errors (any exception with `transient=True`\nattribute). Return the first successful result. Re-raise on\nthe final attempt failure.\n\nExpected output:\n```\nsucceeded on attempt 3\n```\n","grader":{"kind":"stdout-equality","expected":"succeeded on attempt 3","normalize":"collapse-trailing-newline"},"bugLines":[13,14],"revealAfter":5},{"type":"fix","id":"agent-harnesses/what-a-harness-is/s07-07-fix-the-hardcoded-registry","xp":4,"hint":[{"level":1,"body":"Add a `tools` parameter to `dispatch`, drop the hardcoded TOOLS dict, change the lookup to use the parameter, and pass `external_tools` from the call site.","cost":0},{"level":2,"body":"```python\ndef dispatch(tool_use, tools):\n return tools[tool_use[\"name\"]](**tool_use[\"input\"])\n\nresult = dispatch({\"name\": \"search\", \"input\": {\"q\": \"tokyo\"}}, external_tools)\n```\n","cost":0}],"personalize":false,"phase":"build","estSeconds":100,"concept":"inject-tool-registry","brokenCode":"def dispatch(tool_use):\n # bug: tools hardcoded INSIDE the function. adding tools = edits to this body.\n TOOLS = {\n \"search\": lambda q: f\"hits for {q}\",\n }\n return TOOLS[tool_use[\"name\"]](**tool_use[\"input\"])\n\nexternal_tools = {\n \"search\": lambda q: f\"hits for {q}\",\n}\n\nresult = dispatch({\"name\": \"search\", \"input\": {\"q\": \"tokyo\"}})\nprint(result)\n","prompt":"The harness has the tool registry hardcoded INSIDE the loop.\nAdding a new tool means editing the loop function — not a\nmodule-level dict. After three new tools, the loop body is\nunreadable.\n\nFix `dispatch(tool_use, tools)` to take the registry as an\nargument instead of hardcoding it. Then pass the registry in\nfrom outside.\n\nExpected output:\n```\nhits for tokyo\n```\n","grader":{"kind":"stdout-equality","expected":"hits for tokyo","normalize":"collapse-trailing-newline"},"bugLines":[1,7],"revealAfter":4},{"type":"write","id":"agent-harnesses/what-a-harness-is/s08-08-write-mini-harness","xp":5,"hint":[{"level":1,"body":"Same loop shape as previous chapter agent loops, with explicit layer comments. Layer 1: build messages. Loop: layer 2 (call), layer 3 (split content into text/tool_use), branch on stop_reason. On tool_use: layer 4 (dispatch each, append assistant + user turns).","cost":0},{"level":2,"body":"Three counters/buckets: messages list, tool_calls_total int, iter index from `range(1, max_iters + 1)`. End_turn returns the joined text and stats. Cap returns the literal \"capped\".","cost":0}],"personalize":false,"phase":"build","estSeconds":200,"concept":"minimal-four-layer-harness","prompt":"Write `mini_harness(user_input, tools, fake_model, max_iters)`\nthat implements the four layers in under 50 lines:\n\n- **Layer 1**: build `messages = [{\"role\": \"user\", \"content\": user_input}]`.\n- Loop up to `max_iters` times:\n - **Layer 2**: call `fake_model(messages)` (returns a dict\n with `stop_reason` and `content`).\n - **Layer 3**: filter `content` for text blocks (`type==\"text\"`)\n and tool_use blocks (`type==\"tool_use\"`).\n - If `stop_reason == \"end_turn\"`: return\n `{\"text\": , \"iters\": , \"tool_calls\": }`.\n - **Layer 4**: for each tool_use block, dispatch\n `tools[block[\"name\"]](**block[\"input\"])`. Track total tool\n runs. Append assistant + user(tool_results) turns.\n- On cap: return `{\"text\": \"capped\", \"iters\": max_iters, \"tool_calls\": }`.\n\nTwo cases run for you. Expected output:\n```\ntext='Tokyo guide.' iters=2 tool_calls=1\ntext='capped' iters=2 tool_calls=2\n```\n","starter":"$2c","grader":{"kind":"stdout-equality","expected":"text='Tokyo guide.' iters=2 tool_calls=1\ntext='capped' iters=2 tool_calls=2\n","normalize":"collapse-trailing-newline"},"solution":"$2d","hiddenTests":[]},{"type":"checkpoint","id":"agent-harnesses/what-a-harness-is/s09-09-checkpoint","xp":8,"hint":[],"personalize":false,"phase":"check","estSeconds":220,"concept":"harness-with-all-four-layers","prompt":"$2e","starter":"$2f","grader":{"kind":"stdout-equality","expected":"text='Found ramen.' iters=2 tool_calls=1 tokens=130 system_used=True\ntext='capped' iters=2 tool_calls=2 tokens=180 system_used=False\n","normalize":"collapse-trailing-newline"},"solution":"$30","passThreshold":0.66}],"xpTotal":32},{"slug":"architecting-an-ai-native-workflow","title":"Architecting an AI-native workflow — a 5-step playbook in code","estMinutes":15,"prerequisites":["what-a-harness-is"],"status":"live","steps":[{"type":"read","id":"agent-harnesses/architecting-an-ai-native-workflow/s01-01-intro","xp":1,"hint":[],"personalize":false,"phase":"warmup","estSeconds":160,"concept":"ai-assisted-vs-ai-native","body":"$31","cta":"Got it","code":"# the difference between \"ai-assisted\" and \"ai-native\" as a data shape.\nai_assisted_company = {\n \"question\": \"Where can we add AI to save time?\",\n \"ai_lives\": \"at the edges (chatgpt tab, marketing copilot)\",\n \"workflow_design\": \"human-driven, AI sprinkled on top\",\n \"human_role\": \"search engine, router, copywriter\",\n \"metric\": \"hours saved\",\n}\n\nai_native_company = {\n \"question\": \"How should this workflow exist if agents do the first 80%?\",\n \"ai_lives\": \"at the center (agents in the operating fabric)\",\n \"workflow_design\": \"structured, documented, permissioned, instrumented\",\n \"human_role\": \"reviewer of ambiguity, supervisor of judgment\",\n \"metric\": \"resolution_time, conversion_rate, revenue_per_employee\",\n}\n\nfor k in ai_assisted_company:\n a = ai_assisted_company[k]\n n = ai_native_company[k]\n print(f\"{k:18} assisted: {a}\")\n print(f\"{k:18} native: {n}\")\n print()\n","runnable":true},{"type":"mc","id":"agent-harnesses/architecting-an-ai-native-workflow/s02-02-which-workflow-fits","xp":2,"hint":[{"level":1,"body":"Three signals you want: high volume, rules already exist (even informally), and humans currently doing more coordination than judgment. One workflow hits all three.","cost":0}],"personalize":false,"phase":"warmup","estSeconds":60,"concept":"pick-the-right-workflow","prompt":"Step 1 of the playbook: pick a narrow workflow with\nobvious economic value. The criteria: **volume is high, rules\nexist, humans are doing too much coordination.**\n\nFour candidate workflows. Which ONE is the strongest fit?\n","options":[{"id":"a","label":"A — founder vision setting (vol=1, no rules, 5h coord)","explain":"Low volume + no rules + tacit knowledge. This is exactly the work the playbook says you DON'T automate. Strategy is judgment, not workflow."},{"id":"b","label":"B — support ticket triage (vol=4200, rules exist, 80h coord)"},{"id":"c","label":"C — acquiring a competitor (vol=0, no rules)","explain":"Zero volume = not a workflow, it's a project. Agents pay off on repetition; one-off deals don't compound."},{"id":"d","label":"D — quarterly board prep (vol=1, rules exist, 12h coord)","explain":"Rules exist but volume is one per quarter. Cost of structuring exceeds savings. Wait until you have something that runs daily."}],"answerIds":["b"],"shuffle":false,"code":"workflows = {\n \"A\": {\"name\": \"Founder vision setting\", \"volume_per_week\": 1, \"rules_exist\": False, \"human_coord_hours\": 5},\n \"B\": {\"name\": \"Support ticket triage\", \"volume_per_week\": 4200, \"rules_exist\": True, \"human_coord_hours\": 80},\n \"C\": {\"name\": \"Acquiring a competitor\", \"volume_per_week\": 0, \"rules_exist\": False, \"human_coord_hours\": 0},\n \"D\": {\"name\": \"Quarterly board prep\", \"volume_per_week\": 1, \"rules_exist\": True, \"human_coord_hours\": 12},\n}\nfor k, v in workflows.items():\n print(f\"{k}: {v['name']:30} vol={v['volume_per_week']:4} rules={v['rules_exist']} coord_h={v['human_coord_hours']}\")\n","runnable":true},{"type":"read","id":"agent-harnesses/architecting-an-ai-native-workflow/s03-03-mapping-the-workflow","xp":1,"hint":[],"personalize":false,"phase":"build","estSeconds":140,"concept":"workflow-spec-as-data","body":"$32","cta":"Got it","code":"$33","runnable":true},{"type":"predict","id":"agent-harnesses/architecting-an-ai-native-workflow/s04-04-predict-the-readiness-score","xp":3,"hint":[{"level":1,"body":"Count `name`, `trigger`, `inputs`, `decisions`. That's 4 present out of 7 required. `4/7 = 0.5714...`, rounded to 2 decimals is `0.57`.","cost":0},{"level":2,"body":"Output is two lines: `present: 4/7` and `score: 0.57` (three spaces after `score:` because the format string aligns columns).","cost":0}],"personalize":false,"phase":"build","estSeconds":75,"concept":"readiness-score-from-fields","code":"REQUIRED = [\"name\", \"trigger\", \"inputs\", \"decisions\", \"success_criteria\", \"error_sites\", \"tacit_knowledge\"]\n\npartial_spec = {\n \"name\": \"Outbound prospecting\",\n \"trigger\": \"new lead in CRM\",\n \"inputs\": [\"lead.company\", \"lead.role\", \"lead.intent_signals\"],\n \"decisions\": {\"classify_segment\": {\"reversible\": True, \"needs_approval\": False}},\n # success_criteria: missing\n # error_sites: missing\n # tacit_knowledge: missing\n}\n\npresent = [f for f in REQUIRED if f in partial_spec]\nscore = round(len(present) / len(REQUIRED), 2)\n\nprint(f\"present: {len(present)}/{len(REQUIRED)}\")\nprint(f\"score: {score}\")\n","prompt":"The spec has 4 of the 7 required fields. The validator computes\na readiness score as `present / required`, rounded to 2 decimals.\n\nWhat does the script print?\n","grader":{"kind":"stdout-equality","expected":"present: 4/7\nscore: 0.57\n","normalize":"collapse-trailing-newline"}},{"type":"fill","id":"agent-harnesses/architecting-an-ai-native-workflow/s05-05-fill-the-required-fields","xp":3,"hint":[{"level":1,"body":"Seven strings in a list, in the order: name, trigger, inputs, decisions, success_criteria, error_sites, tacit_knowledge.","cost":0},{"level":2,"body":"`['name', 'trigger', 'inputs', 'decisions', 'success_criteria', 'error_sites', 'tacit_knowledge']` — single quotes match the expected output.","cost":0}],"personalize":false,"phase":"build","estSeconds":70,"concept":"required-spec-fields","prompt":"Fill the list of the SEVEN required spec fields a workflow needs\nto be machine-readable. Order matches the lesson: name, trigger,\ninputs, decisions, success_criteria, error_sites, tacit_knowledge.\n\nExpected output:\n```\n['name', 'trigger', 'inputs', 'decisions', 'success_criteria', 'error_sites', 'tacit_knowledge']\n```\n","code":"REQUIRED = ___\nprint(REQUIRED)\n","blanks":[{"id":"required_list","accept":["['name', 'trigger', 'inputs', 'decisions', 'success_criteria', 'error_sites', 'tacit_knowledge']","[\"name\", \"trigger\", \"inputs\", \"decisions\", \"success_criteria\", \"error_sites\", \"tacit_knowledge\"]"],"caseSensitive":true,"normalize":"trim"}]},{"type":"fix","id":"agent-harnesses/architecting-an-ai-native-workflow/s06-06-fix-the-implicit-policy","xp":4,"hint":[{"level":1,"body":"Replace the string with a dict. Two keys: `auto_approve_under` and `requires_human_above`, both pointing at the same number (100). The agent now has a rule to follow.","cost":0},{"level":2,"body":"`workflow[\"refund_policy\"] = {\"auto_approve_under\": 100, \"requires_human_above\": 100}`. Print prints the dict in insertion order (Python 3.7+).","cost":0}],"personalize":false,"phase":"build","estSeconds":100,"concept":"implicit-to-explicit-rule","brokenCode":"workflow = {\n \"name\": \"Refund processing\",\n # bug: \"ask the support lead\" is not a policy. an agent cannot\n # ground in tribal knowledge. encode the rule explicitly.\n \"refund_policy\": \"ask the support lead\",\n}\n\nprint(workflow[\"refund_policy\"])\n","prompt":"A canonical implicit-policy failure: \"the sales process is 'talk\nto Sarah, she knows how we do enterprise.'\" That's tribal\nknowledge. An agent can't ask Sarah. The fix is to make Sarah's\nknowledge explicit as a data rule.\n\nThe spec below has `refund_policy = \"ask the support lead\"`. An\nagent reading this has nothing to ground in. Replace it with an\nexplicit rule dict containing `auto_approve_under` (dollar\nthreshold below which the agent can refund without human review)\nand `requires_human_above` (the same threshold). Use $100.\n\nExpected output:\n```\n{'auto_approve_under': 100, 'requires_human_above': 100}\n```\n","grader":{"kind":"stdout-equality","expected":"{'auto_approve_under': 100, 'requires_human_above': 100}","normalize":"collapse-trailing-newline"},"bugLines":[5],"revealAfter":4},{"type":"fix","id":"agent-harnesses/architecting-an-ai-native-workflow/s07-07-fix-the-wrong-metric","xp":4,"hint":[{"level":1,"body":"Replace the list with `['resolution_time_minutes', 'csat']`. Both show up in the customer's experience and on the company's dashboard.","cost":0},{"level":2,"body":"`workflow[\"metrics\"] = [\"resolution_time_minutes\", \"csat\"]`. Hours saved is what you tell investors before they ask for revenue numbers; resolution_time and csat are what they ask for next.","cost":0}],"personalize":false,"phase":"build","estSeconds":95,"concept":"business-metric-not-hours-saved","brokenCode":"workflow = {\n \"name\": \"Support triage\",\n # bug: \"hours saved\" is a fake metric. business impact is\n # resolution_time, conversion_rate, csat, revenue_per_employee.\n \"metrics\": [\"hours_saved_per_week\"],\n}\n\nprint(workflow[\"metrics\"])\n","prompt":"Step 5 of the playbook is the one most teams botch: measure\nbusiness impact, NOT \"hours saved.\" Hours saved is a vanity metric\na PM invents to justify a project; it doesn't show up on the\nincome statement.\n\nThe spec below tracks `hours_saved_per_week`. Replace it with two\nreal business metrics: `resolution_time_minutes` (median time to\nresolve a ticket) and `csat` (customer satisfaction, 1-5).\n\nExpected output (the two business metrics):\n```\n['resolution_time_minutes', 'csat']\n```\n","grader":{"kind":"stdout-equality","expected":"['resolution_time_minutes', 'csat']","normalize":"collapse-trailing-newline"},"bugLines":[5],"revealAfter":4},{"type":"write","id":"agent-harnesses/architecting-an-ai-native-workflow/s08-08-write-the-workflow-validator","xp":5,"hint":[{"level":1,"body":"Five returned keys. Build `missing` as a sorted list so output is deterministic. `has_explicit_policies` defaults to True when there are no policies (empty dict).","cost":0},{"level":2,"body":"`has_explicit_policies = all(isinstance(v, dict) for v in policies.values())` if policies else True. `business_metrics_only = not any(m in VANITY for m in metrics)`. `ready` is the AND of three signals.","cost":0}],"personalize":false,"phase":"build","estSeconds":200,"concept":"workflow-spec-validator","prompt":"Write `is_ai_native_ready(spec)` that returns a dict with:\n\n- `score`: float, fraction of REQUIRED fields present (rounded to 2)\n- `missing`: list of required field names not in the spec\n- `has_explicit_policies`: True iff EVERY value in\n `spec.get(\"policies\", {})` is a dict (not a string — \"ask Sarah\"\n is a string and disqualifies)\n- `business_metrics_only`: True iff `spec.get(\"metrics\", [])` contains\n NONE of these vanity strings: `\"hours_saved\"`, `\"hours_saved_per_week\"`,\n `\"engagement\"`, `\"vibes\"`\n- `ready`: True iff score >= 0.85 AND has_explicit_policies AND\n business_metrics_only\n\nTwo specs run. Expected output:\n```\n{'score': 1.0, 'missing': [], 'has_explicit_policies': True, 'business_metrics_only': True, 'ready': True}\n{'score': 0.43, 'missing': ['decisions', 'error_sites', 'success_criteria', 'tacit_knowledge'], 'has_explicit_policies': False, 'business_metrics_only': False, 'ready': False}\n```\n","starter":"REQUIRED = [\"name\", \"trigger\", \"inputs\", \"decisions\", \"success_criteria\", \"error_sites\", \"tacit_knowledge\"]\nVANITY = {\"hours_saved\", \"hours_saved_per_week\", \"engagement\", \"vibes\"}\n\ngood_spec = {\n \"name\": \"Support triage\",\n \"trigger\": \"ticket.created\",\n \"inputs\": [\"ticket.body\", \"customer.history\"],\n \"decisions\": {\"classify\": {\"reversible\": True, \"needs_approval\": False}},\n \"success_criteria\": \"first-response < 10min\",\n \"error_sites\": [\"wrong-account retrieval\"],\n \"tacit_knowledge\": \"tone with angry-but-right customers\",\n \"policies\": {\"refund\": {\"auto_approve_under\": 100}},\n \"metrics\": [\"resolution_time_minutes\", \"csat\"],\n}\n\nvibe_spec = {\n \"name\": \"Sales outreach\",\n \"trigger\": \"lead.created\",\n \"inputs\": [\"lead.company\"],\n \"policies\": {\"who_to_contact\": \"ask Sarah, she knows\"},\n \"metrics\": [\"hours_saved_per_week\"],\n}\n\n# define is_ai_native_ready(spec) below\n\nprint(is_ai_native_ready(good_spec))\nprint(is_ai_native_ready(vibe_spec))\n","grader":{"kind":"stdout-equality","expected":"{'score': 1.0, 'missing': [], 'has_explicit_policies': True, 'business_metrics_only': True, 'ready': True}\n{'score': 0.43, 'missing': ['decisions', 'error_sites', 'success_criteria', 'tacit_knowledge'], 'has_explicit_policies': False, 'business_metrics_only': False, 'ready': False}\n","normalize":"collapse-trailing-newline"},"solution":"$34","hiddenTests":[]},{"type":"checkpoint","id":"agent-harnesses/architecting-an-ai-native-workflow/s09-09-checkpoint","xp":8,"hint":[],"personalize":false,"phase":"check","estSeconds":220,"concept":"triage-three-workflow-specs","prompt":"Final drill. Three workflow specs from three teams who want to\ngo AI-native. Score each one with `is_ai_native_ready` from step\n08. Print a one-line verdict per spec: `READY` or\n`NOT READY: `.\n\nReason is the FIRST failing check, in this priority order:\n1. score < 0.85 -> `\"incomplete spec (score=X)\"`\n2. not has_explicit_policies -> `\"implicit policy\"`\n3. not business_metrics_only -> `\"vanity metric\"`\n\nThree specs run. Expected output:\n```\nSupport: READY\nSales: NOT READY: implicit policy\nOnboard: NOT READY: incomplete spec (score=0.57)\n```\n","starter":"$35","grader":{"kind":"stdout-equality","expected":"Support: READY\nSales: NOT READY: implicit policy\nOnboard: NOT READY: incomplete spec (score=0.57)\n","normalize":"collapse-trailing-newline"},"solution":"$36","passThreshold":0.66}],"xpTotal":31},{"slug":"five-industries-walked-through","title":"Five industries walked through — what AI-native looks like in the wild","estMinutes":20,"prerequisites":["architecting-an-ai-native-workflow"],"status":"live","steps":[{"type":"read","id":"agent-harnesses/five-industries-walked-through/s01-01-the-case-study-method","xp":1,"hint":[],"personalize":false,"phase":"warmup","estSeconds":180,"concept":"case-study-method","body":"$37","cta":"Got it","runnable":true},{"type":"read","id":"agent-harnesses/five-industries-walked-through/s02-02-home-services","xp":1,"hint":[],"personalize":false,"phase":"warmup","estSeconds":200,"concept":"case-study-home-services","body":"$38","cta":"Got it","runnable":true},{"type":"mc","id":"agent-harnesses/five-industries-walked-through/s03-03-which-task-belongs-to-the-agent","xp":2,"hint":[{"level":1,"body":"The general rule (echoing Isenberg's writing on AI-native services): agents handle structured work, humans handle taste, trust, judgment, relationships, exceptions. Firing someone and lawyer-negotiation are both 100% judgment + relationships.","cost":0}],"personalize":false,"phase":"build","estSeconds":55,"concept":"agent-vs-human-task-split","prompt":"Five tasks from the home-services rebuild. Three of them belong to\nthe agent (structured work). Two of them belong to a human (taste,\ntrust, judgment, relationships, exceptions).\n\nWhich TWO should stay with humans?\n","options":[{"id":"2_and_4","label":"2 (fire a tech) and 4 (negotiate with a lawyer)"},{"id":"1_and_5","label":"1 (classify call) and 5 (generate invoice)","explain":"Both are structured tasks with explicit rules. Classification is a canonical agent job; invoice drafting is mechanical given a job-done signal. Humans don't need to do either."},{"id":"3_and_4","label":"3 (look up history) and 4 (negotiate with a lawyer)","explain":"Customer-history lookup is exactly what agents are best at — read structured records and synthesize. Don't waste a human on it."},{"id":"1_and_2","label":"1 (classify call) and 2 (fire a tech)","explain":"Half right. Firing a tech is judgment. But classifying calls is the agent's whole reason to exist in this workflow."}],"answerIds":["2_and_4"],"shuffle":false,"code":"# five tasks from the home-services workflow. who should own each?\ntasks = [\n \"Classify an incoming call as emergency vs scheduled\",\n \"Decide whether to fire a long-tenured tech for repeated rudeness\",\n \"Look up the customer's prior service history and draft a job brief\",\n \"Negotiate a one-off discount with the customer's lawyer over a disputed invoice\",\n \"Generate the invoice draft when the tech says the job is done\",\n]\nfor i, t in enumerate(tasks, 1):\n print(f\"{i}. {t}\")\n","runnable":true},{"type":"read","id":"agent-harnesses/five-industries-walked-through/s04-04-insurance-brokerage","xp":1,"hint":[],"personalize":false,"phase":"build","estSeconds":220,"concept":"case-study-insurance-brokerage","body":"$39","cta":"Got it","runnable":true},{"type":"read","id":"agent-harnesses/five-industries-walked-through/s05-05-recruiting-firm","xp":1,"hint":[],"personalize":false,"phase":"build","estSeconds":200,"concept":"case-study-recruiting","body":"$3a","cta":"Got it","runnable":true},{"type":"mc","id":"agent-harnesses/five-industries-walked-through/s06-06-which-industry-wedges-fastest","xp":2,"hint":[{"level":1,"body":"The wedge profile is: HIGH volume, EXPLICIT rules (so the agent has something to ground in), STRUCTURED outcomes (recurring shapes, not one-off bespoke work). Only one of the four hits all three.","cost":0}],"personalize":false,"phase":"build","estSeconds":70,"concept":"pick-the-fastest-wedge","prompt":"Four candidate industries for an AI-native rebuild. Per the\ncase-study method (high volume + explicit rules + structured\noutcomes), which ONE wedges in fastest?\n","options":[{"id":"a","label":"A — boutique M&A law firm","explain":"Low volume + mostly tacit rules + high-stakes outcomes. This is the OPPOSITE of the wedge profile. The cost of structuring the workflow exceeds the savings; the irreversible-outcome nature means humans can't be removed."},{"id":"b","label":"B — bookkeeping for SMBs"},{"id":"c","label":"C — PR agency","explain":"Taste-driven and relationship-heavy. Agents can draft, but the value the client buys is the human taste behind the pitch. Volume's also medium, not high."},{"id":"d","label":"D — investment banking capital markets","explain":"Low volume + heavily regulated + brand-risk on every output. Worst possible profile for an agent-first rebuild."}],"answerIds":["b"],"shuffle":false,"code":"$3b","runnable":true},{"type":"read","id":"agent-harnesses/five-industries-walked-through/s07-07-the-incumbent-trap","xp":1,"hint":[],"personalize":false,"phase":"build","estSeconds":200,"concept":"process-debt-and-the-incumbent-trap","body":"$3c","cta":"Got it","runnable":true},{"type":"write","id":"agent-harnesses/five-industries-walked-through/s08-08-write-the-process-debt-audit","xp":5,"hint":[{"level":1,"body":"Six conditionals, each adds a fixed number of points. Use `.get()` with defaults so missing fields don't crash. Then four-way threshold for the verdict.","cost":0},{"level":2,"body":"HVAC Inc hits all six conditions: 25 (old) + 20 (scattered) + 20 (tacit) + 15 (paper) + 10 (overstaffed) + 10 (undocumented) = 100. StartupCo hits zero conditions, score 0. The verdict thresholds: <=20 ready, <=50 manageable, <=80 heavy, >80 trap.","cost":0}],"personalize":false,"phase":"build","estSeconds":200,"concept":"process-debt-scoring","prompt":"Write `process_debt_score(company)` that takes a company profile\n(dict) and returns a dict with two fields:\n\n- `score`: integer 0-100, higher means MORE process debt (bad)\n- `verdict`: string, one of:\n - `\"AI-native ready\"` if score <= 20\n - `\"manageable debt\"` if score <= 50\n - `\"heavy debt\"` if score <= 80\n - `\"incumbent trap\"` if score > 80\n\nScore the company on these signals (each adds points to the debt\ntotal):\n\n- `age_years > 10`: add 25 (incumbent business — typical 20+ year history)\n- `data_scattered_across_tools >= 5`: add 20 (CRM + Slack + email + spreadsheets...)\n- `tacit_knowledge_pct > 50`: add 20 (more than half of company knowledge \"in someone's head\")\n- `paper_processes > 0`: add 15 (any paper at all)\n- `headcount_per_revenue_million > 7`: add 10 (overstaffed)\n- `documented_workflows_pct < 30`: add 10 (mostly undocumented)\n\nTwo companies run. Expected output:\n```\nHVAC Inc: {'score': 100, 'verdict': 'incumbent trap'}\nStartupCo: {'score': 0, 'verdict': 'AI-native ready'}\n```\n","starter":"hvac_inc = {\n \"name\": \"HVAC Inc\",\n \"age_years\": 22,\n \"data_scattered_across_tools\": 6,\n \"tacit_knowledge_pct\": 65,\n \"paper_processes\": 2,\n \"headcount_per_revenue_million\": 8,\n \"documented_workflows_pct\": 15,\n}\n\nstartup_co = {\n \"name\": \"StartupCo\",\n \"age_years\": 1,\n \"data_scattered_across_tools\": 2,\n \"tacit_knowledge_pct\": 30,\n \"paper_processes\": 0,\n \"headcount_per_revenue_million\": 4,\n \"documented_workflows_pct\": 80,\n}\n\n# define process_debt_score(company) below\n\nprint(f\"HVAC Inc: {process_debt_score(hvac_inc)}\")\nprint(f\"StartupCo: {process_debt_score(startup_co)}\")\n","grader":{"kind":"stdout-equality","expected":"HVAC Inc: {'score': 100, 'verdict': 'incumbent trap'}\nStartupCo: {'score': 0, 'verdict': 'AI-native ready'}\n","normalize":"collapse-trailing-newline"},"solution":"$3d","hiddenTests":[]},{"type":"checkpoint","id":"agent-harnesses/five-industries-walked-through/s09-09-checkpoint","xp":8,"hint":[],"personalize":false,"phase":"check","estSeconds":240,"concept":"synthesize-the-case-study-method","prompt":"Final drill. Synthesize the case-study method into one function:\n`pick_industry(candidates)` that takes a list of industry profiles\nand returns the name of the BEST candidate for an AI-native\nrebuild.\n\nEach candidate is a dict with:\n- `name`: string\n- `volume_per_week`: int\n- `rules_explicit`: bool\n- `outcome_structured`: bool\n- `incumbent_avg_age_years`: int\n\nScore each candidate using these rules (higher = better wedge):\n\n- `volume_per_week >= 100`: +30\n- `rules_explicit`: +25\n- `outcome_structured`: +25\n- `incumbent_avg_age_years >= 20`: +20 (incumbent trap is biggest)\n\nReturn the name of the highest-scoring candidate. On a tie, return\nthe FIRST one (Python's `max` with `key=` preserves stable order).\n\nFive candidates run. Expected output:\n```\nbest: Insurance brokerage\n```\n","starter":"candidates = [\n {\"name\": \"Boutique law firm\", \"volume_per_week\": 2, \"rules_explicit\": False, \"outcome_structured\": False, \"incumbent_avg_age_years\": 30},\n {\"name\": \"Insurance brokerage\", \"volume_per_week\": 200, \"rules_explicit\": True, \"outcome_structured\": True, \"incumbent_avg_age_years\": 35},\n {\"name\": \"PR agency\", \"volume_per_week\": 40, \"rules_explicit\": False, \"outcome_structured\": False, \"incumbent_avg_age_years\": 15},\n {\"name\": \"Bookkeeping for SMBs\", \"volume_per_week\": 300, \"rules_explicit\": True, \"outcome_structured\": True, \"incumbent_avg_age_years\": 18},\n {\"name\": \"VC investing\", \"volume_per_week\": 1, \"rules_explicit\": False, \"outcome_structured\": False, \"incumbent_avg_age_years\": 25},\n]\n\n# define pick_industry(candidates) below\n\nprint(f\"best: {pick_industry(candidates)}\")\n","grader":{"kind":"stdout-equality","expected":"best: Insurance brokerage","normalize":"collapse-trailing-newline"},"solution":"$3e","passThreshold":0.66}],"xpTotal":22},{"slug":"incident-runbook-from-the-repo","title":"Incident runbook from the repo — detect, decide rollback, write back","estMinutes":14,"prerequisites":["what-a-harness-is"],"status":"live","steps":[{"type":"read","id":"agent-harnesses/incident-runbook-from-the-repo/s01-01-intro","xp":1,"hint":[],"personalize":false,"phase":"warmup","estSeconds":140,"concept":"wiki-vs-repo-runbook","body":"$3f","cta":"Got it","code":"# two artifacts that both get called a \"runbook.\"\n# only one can be executed from the repo at 3am.\n\nwiki = \"if the nightly batch looks bad, use your judgment\"\n\nrunbook = {\n \"detect\": {\"signal\": \"error_rate\", \"rollback_if_at_least\": 0.08},\n \"named_human\": \"release-owner\",\n \"writeback\": \"incidents/log.jsonl\",\n}\n\nprint(\"wiki: a page a junior has to interpret\")\nprint(\n f\"runbook: detect={runbook['detect']['signal']} \"\n f\"rollback_if>={runbook['detect']['rollback_if_at_least']} \"\n f\"human={runbook['named_human']} \"\n f\"writeback={runbook['writeback']}\"\n)\n","runnable":true},{"type":"mc","id":"agent-harnesses/incident-runbook-from-the-repo/s02-02-which-is-a-runbook","xp":2,"hint":[{"level":1,"body":"The discriminator is executability. Can a junior (or a harness) read one artifact and know detect / decide / who / writeback without inventing a process?","cost":0}],"personalize":false,"phase":"warmup","estSeconds":55,"concept":"executable-runbook-shape","prompt":"A runbook a junior can execute from the repo has to be data:\na signal to detect, a rollback-versus-continue rule, a named\nhuman if the decision cannot be executed alone, and a path\nto write the record back. Which ONE of the artifacts above\nis that runbook?\n","options":[{"id":"a","label":"A — the Notion page","explain":"A page a junior has to interpret is still a wiki. 'Maybe' and 'find someone' are not a threshold or a named seat."},{"id":"b","label":"B — the dict in the repo"},{"id":"c","label":"C — last month's Slack thread","explain":"A thread is a story about one night. It is not a rule the next junior can execute, and nothing gets written back to the repo."},{"id":"d","label":"D — 'use your judgment'","explain":"'The team' is not a named human, and judgment is what the runbook is supposed to replace at 3am."}],"answerIds":["b"],"shuffle":false,"code":"artifacts = {\n \"A\": \"A Notion page: 'if the nightly batch looks bad, maybe roll back or find someone.'\",\n \"B\": \"A dict in the repo: detect.error_rate, rollback_if_at_least=0.08, named_human=release-owner, writeback=incidents/log.jsonl.\",\n \"C\": \"Last month's Slack thread, pinned, titled 'what we did last time'.\",\n \"D\": \"A wiki heading: 'Use your judgment. Page the team if unsure.'\",\n}\nfor k, v in artifacts.items():\n print(f\"{k}: {v}\")\n","runnable":true},{"type":"read","id":"agent-harnesses/incident-runbook-from-the-repo/s03-03-detect-decide-writeback","xp":2,"hint":[],"personalize":false,"phase":"build","estSeconds":120,"concept":"detect-decide-writeback","body":"$40","cta":"Got it","code":"# the decision table a junior runs. rollback is the default\n# once the signal crosses the line. escalate only when\n# rollback itself cannot run.\n\nTHRESHOLD = 0.08\nincidents = [\n {\"id\": \"INC-041\", \"error_rate\": 0.12, \"rollback_blocked\": False},\n {\"id\": \"INC-042\", \"error_rate\": 0.03, \"rollback_blocked\": False},\n {\"id\": \"INC-043\", \"error_rate\": 0.15, \"rollback_blocked\": True},\n]\n\ndef decide(inc):\n if inc[\"rollback_blocked\"]:\n return \"escalate\"\n if inc[\"error_rate\"] >= THRESHOLD:\n return \"rollback\"\n return \"continue\"\n\nfor inc in incidents:\n print(f\"{inc['id']} {decide(inc)}\")\n","runnable":true},{"type":"predict","id":"agent-harnesses/incident-runbook-from-the-repo/s04-04-predict-the-decision","xp":3,"hint":[{"level":1,"body":"Blocked is checked first — INC-043 escalates even though 0.15 is over the line. 0.12 >= 0.08 is rollback. 0.03 is continue.","cost":0}],"personalize":false,"phase":"build","estSeconds":75,"concept":"classify-incident-decision","code":"THRESHOLD = 0.08\nincidents = [\n {\"id\": \"INC-041\", \"error_rate\": 0.12, \"rollback_blocked\": False},\n {\"id\": \"INC-042\", \"error_rate\": 0.03, \"rollback_blocked\": False},\n {\"id\": \"INC-043\", \"error_rate\": 0.15, \"rollback_blocked\": True},\n]\n\ndef decide(inc):\n if inc[\"rollback_blocked\"]:\n return \"escalate\"\n if inc[\"error_rate\"] >= THRESHOLD:\n return \"rollback\"\n return \"continue\"\n\nfor inc in incidents:\n print(f\"{inc['id']} {decide(inc)}\")\n","prompt":"Read the editor. Three incidents, one threshold (0.08),\nrollback blocked only on INC-043. What does the script\nprint?\n","grader":{"kind":"stdout-equality","expected":"INC-041 rollback\nINC-042 continue\nINC-043 escalate\n","normalize":"collapse-trailing-newline"}},{"type":"fill","id":"agent-harnesses/incident-runbook-from-the-repo/s05-05-fill-the-decision-rule","xp":3,"hint":[{"level":1,"body":"Look up the signal name, then compare it to `rollback_if_at_least`. Do not hardcode `error_rate` or `0.08`.","cost":0},{"level":2,"body":"`signals[runbook[\"detect\"][\"signal\"]] >= runbook[\"detect\"][\"rollback_if_at_least\"]`","cost":0}],"personalize":false,"phase":"build","estSeconds":70,"concept":"rollback-threshold-rule","prompt":"Fill the rollback comparison. Read the signal name and the\nthreshold from the runbook — do not hardcode `error_rate`\nor `0.08`. Escalate is already handled.\n\nExpected output:\n```\nrollback\ncontinue\n```\n","code":"runbook = {\n \"detect\": {\"signal\": \"error_rate\", \"rollback_if_at_least\": 0.08},\n}\n\ndef decide(signals, runbook):\n if signals.get(\"rollback_blocked\"):\n return \"escalate\"\n if ___:\n return \"rollback\"\n return \"continue\"\n\nprint(decide({\"error_rate\": 0.12}, runbook))\nprint(decide({\"error_rate\": 0.03}, runbook))\n","blanks":[{"id":"threshold_check","accept":["signals[runbook[\"detect\"][\"signal\"]] >= runbook[\"detect\"][\"rollback_if_at_least\"]","signals[runbook['detect']['signal']] >= runbook['detect']['rollback_if_at_least']"],"caseSensitive":true,"normalize":"trim"}]},{"type":"fix","id":"agent-harnesses/incident-runbook-from-the-repo/s06-06-fix-the-wiki-page","xp":4,"hint":[{"level":1,"body":"Replace the string with a dict. Four keys: `detect` (the signal name), `rollback_if_at_least` (0.08), `named_human` (`release-owner`), `writeback` (`incidents/log.jsonl`).","cost":0},{"level":2,"body":"```python\nrunbook = {\n \"detect\": \"error_rate\",\n \"rollback_if_at_least\": 0.08,\n \"named_human\": \"release-owner\",\n \"writeback\": \"incidents/log.jsonl\",\n}\n```\n","cost":0}],"personalize":false,"phase":"build","estSeconds":100,"concept":"runbook-as-data-not-prose","brokenCode":"# bug: a wiki sentence is not a runbook. a junior cannot\n# execute prose. encode detect / threshold / human / path.\nrunbook = \"if the nightly batch looks bad, use your judgment\"\n\nprint(runbook[\"detect\"])\nprint(runbook[\"rollback_if_at_least\"])\nprint(runbook[\"named_human\"])\nprint(runbook[\"writeback\"])\n","prompt":"The \"runbook\" is a sentence. A junior cannot execute a\nsentence. Replace it with a dict that has the four fields\na checkout can follow: `detect`, `rollback_if_at_least`,\n`named_human`, `writeback`.\n\nUse `error_rate`, `0.08`, `release-owner`, and\n`incidents/log.jsonl`. The print statements stay as they\nare — they read those four keys.\n\nExpected output:\n```\nerror_rate\n0.08\nrelease-owner\nincidents/log.jsonl\n```\n","grader":{"kind":"stdout-equality","expected":"error_rate\n0.08\nrelease-owner\nincidents/log.jsonl\n","normalize":"collapse-trailing-newline"},"bugLines":[3],"revealAfter":4},{"type":"fix","id":"agent-harnesses/incident-runbook-from-the-repo/s07-07-fix-the-unnamed-human","xp":4,"hint":[{"level":1,"body":"On escalate, return `runbook[\"named_human\"]`. Leave the `return \"runbook\"` branch for rollback and continue.","cost":0},{"level":2,"body":"Replace `return \"the team\"` with `return runbook[\"named_human\"]`.","cost":0}],"personalize":false,"phase":"build","estSeconds":95,"concept":"named-human-not-the-team","brokenCode":"runbook = {\"named_human\": \"release-owner\"}\n\ndef actor_for(decision, runbook):\n # bug: \"the team\" is not a named human. escalate has\n # to resolve to a seat the junior can actually page.\n if decision == \"escalate\":\n return \"the team\"\n return \"runbook\"\n\nprint(actor_for(\"escalate\", runbook))\nprint(actor_for(\"rollback\", runbook))\nprint(actor_for(\"continue\", runbook))\n","prompt":"Escalate currently pages `\"the team\"`. That is a channel,\nnot a person. A junior cannot execute \"page the team.\"\nReturn `runbook[\"named_human\"]` on escalate, and\n`\"runbook\"` on every decision the checkout can finish\nalone.\n\nExpected output:\n```\nrelease-owner\nrunbook\nrunbook\n```\n","grader":{"kind":"stdout-equality","expected":"release-owner\nrunbook\nrunbook\n","normalize":"collapse-trailing-newline"},"bugLines":[7],"revealAfter":4},{"type":"write","id":"agent-harnesses/incident-runbook-from-the-repo/s08-08-write-the-runbook","xp":5,"hint":[{"level":1,"body":"Blocked first, then threshold, then continue. Actor is the named human only on escalate. Artifact is the writeback path.","cost":0},{"level":2,"body":"Build a dict with those five keys in that order so `print` matches. Look up the signal with `signals[runbook[\"detect\"][\"signal\"]]`.","cost":0}],"personalize":false,"phase":"build","estSeconds":200,"concept":"execute-runbook","prompt":"Write `execute_runbook(signals, runbook)` that returns a\nwriteback record — the dict a junior would append to the\nrepo. Fields:\n\n- `id`: `signals[\"id\"]`\n- `decision`: `\"escalate\"` if `signals.get(\"rollback_blocked\")`;\n `\"rollback\"` if the detect signal is >=\n `rollback_if_at_least`; otherwise `\"continue\"`\n- `signal`: the detect signal's value\n- `actor`: `runbook[\"named_human\"]` on escalate, else\n `\"runbook\"`\n- `artifact`: `runbook[\"writeback\"][\"path\"]`\n\nTwo incidents run. Expected output:\n```\n{'id': 'INC-041', 'decision': 'rollback', 'signal': 0.12, 'actor': 'runbook', 'artifact': 'incidents/log.jsonl'}\n{'id': 'INC-043', 'decision': 'escalate', 'signal': 0.15, 'actor': 'release-owner', 'artifact': 'incidents/log.jsonl'}\n```\n","starter":"RUNBOOK = {\n \"detect\": {\"signal\": \"error_rate\", \"rollback_if_at_least\": 0.08},\n \"named_human\": \"release-owner\",\n \"writeback\": {\"path\": \"incidents/log.jsonl\"},\n}\n\ninc_041 = {\"id\": \"INC-041\", \"error_rate\": 0.12, \"rollback_blocked\": False}\ninc_043 = {\"id\": \"INC-043\", \"error_rate\": 0.15, \"rollback_blocked\": True}\n\n# define execute_runbook(signals, runbook) below\n\nprint(execute_runbook(inc_041, RUNBOOK))\nprint(execute_runbook(inc_043, RUNBOOK))\n","grader":{"kind":"stdout-equality","expected":"{'id': 'INC-041', 'decision': 'rollback', 'signal': 0.12, 'actor': 'runbook', 'artifact': 'incidents/log.jsonl'}\n{'id': 'INC-043', 'decision': 'escalate', 'signal': 0.15, 'actor': 'release-owner', 'artifact': 'incidents/log.jsonl'}\n","normalize":"collapse-trailing-newline"},"solution":"RUNBOOK = {\n \"detect\": {\"signal\": \"error_rate\", \"rollback_if_at_least\": 0.08},\n \"named_human\": \"release-owner\",\n \"writeback\": {\"path\": \"incidents/log.jsonl\"},\n}\n\ninc_041 = {\"id\": \"INC-041\", \"error_rate\": 0.12, \"rollback_blocked\": False}\ninc_043 = {\"id\": \"INC-043\", \"error_rate\": 0.15, \"rollback_blocked\": True}\n\ndef execute_runbook(signals, runbook):\n detect = runbook[\"detect\"]\n if signals.get(\"rollback_blocked\"):\n decision = \"escalate\"\n elif signals[detect[\"signal\"]] >= detect[\"rollback_if_at_least\"]:\n decision = \"rollback\"\n else:\n decision = \"continue\"\n actor = runbook[\"named_human\"] if decision == \"escalate\" else \"runbook\"\n return {\n \"id\": signals[\"id\"],\n \"decision\": decision,\n \"signal\": signals[detect[\"signal\"]],\n \"actor\": actor,\n \"artifact\": runbook[\"writeback\"][\"path\"],\n }\n\nprint(execute_runbook(inc_041, RUNBOOK))\nprint(execute_runbook(inc_043, RUNBOOK))\n","hiddenTests":[]},{"type":"checkpoint","id":"agent-harnesses/incident-runbook-from-the-repo/s09-09-checkpoint","xp":8,"hint":[],"personalize":false,"phase":"check","estSeconds":220,"concept":"three-incident-writebacks","prompt":"Final drill. Run all three incidents through\n`execute_runbook` from step 08. Print one writeback line\nper incident:\n\n`{id} {decision} actor={actor} artifact={artifact}`\n\nSame runbook. Same rules: blocked → escalate and name\n`release-owner`; at or above 0.08 → rollback; else\ncontinue. Actor is `runbook` unless escalate fired.\n\nThree incidents run. Expected output:\n```\nINC-041 rollback actor=runbook artifact=incidents/log.jsonl\nINC-042 continue actor=runbook artifact=incidents/log.jsonl\nINC-043 escalate actor=release-owner artifact=incidents/log.jsonl\n```\n","starter":"RUNBOOK = {\n \"detect\": {\"signal\": \"error_rate\", \"rollback_if_at_least\": 0.08},\n \"named_human\": \"release-owner\",\n \"writeback\": {\"path\": \"incidents/log.jsonl\"},\n}\n\nincidents = [\n {\"id\": \"INC-041\", \"error_rate\": 0.12, \"rollback_blocked\": False},\n {\"id\": \"INC-042\", \"error_rate\": 0.03, \"rollback_blocked\": False},\n {\"id\": \"INC-043\", \"error_rate\": 0.15, \"rollback_blocked\": True},\n]\n\ndef execute_runbook(signals, runbook):\n detect = runbook[\"detect\"]\n if signals.get(\"rollback_blocked\"):\n decision = \"escalate\"\n elif signals[detect[\"signal\"]] >= detect[\"rollback_if_at_least\"]:\n decision = \"rollback\"\n else:\n decision = \"continue\"\n actor = runbook[\"named_human\"] if decision == \"escalate\" else \"runbook\"\n return {\n \"id\": signals[\"id\"],\n \"decision\": decision,\n \"signal\": signals[detect[\"signal\"]],\n \"actor\": actor,\n \"artifact\": runbook[\"writeback\"][\"path\"],\n }\n\n# print one writeback line per incident\n","grader":{"kind":"stdout-equality","expected":"INC-041 rollback actor=runbook artifact=incidents/log.jsonl\nINC-042 continue actor=runbook artifact=incidents/log.jsonl\nINC-043 escalate actor=release-owner artifact=incidents/log.jsonl\n","normalize":"collapse-trailing-newline"},"solution":"$41","passThreshold":0.66}],"xpTotal":32}],"liveLessonCount":5,"liveStepCount":37,"xpTotal":119}},"chapter":"$1c:2:props:tree:detail","lesson":"$1c:2:props:tree:detail:lessons:2","step":"$1c:2:props:tree:detail:lessons:2:steps:3","stepIndex":3,"nav":{"tocNext":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":4},"tocPrev":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":2},"nextByPath":{"developer":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":4},"marketer":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":4},"designer":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":4},"customer-service":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":4},"copywriter":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":4},"data-analyst":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":4},"project-manager":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":4},"hr-specialist":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":4},"operations":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":4},"lawyer":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":4}},"prevByPath":{"developer":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":2},"marketer":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":2},"designer":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":2},"customer-service":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":2},"copywriter":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":2},"data-analyst":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":2},"project-manager":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":2},"hr-specialist":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":2},"operations":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":2},"lawyer":{"chapterSlug":"agent-harnesses","lessonSlug":"architecting-an-ai-native-workflow","stepIndex":2}}}}]]

Architecting an AI-native workflow — a 5-step playbook in code — step 4 of 9