The harness-engineering mindset — Agent equals Model plus Harness — step 8 of 8
One last thing before we move on. Same surface as a write step — but the lesson doesn't complete until this passes.
Final drill for the mindset lesson. Write triage_harnesses(harnesses)
that scores five harness configurations and returns a dict:
scores: dict mapping each harnessname→ its 0-100 score (insertion order preserved)weakest: the name of the harness MOST likely to fail first (lowest score). On a tie, return the FIRST one in input order.
Reuse the six-piece scoring from the previous drill:
- Each present piece (
config,tools,infra,orchestration,hooks,observability) adds 16. - All six present → 100.
Five harnesses run for you. Expected output:
scores: {'claude-code-pro': 100, 'cursor-default': 64, 'aider-basic': 32, 'raw-anthropic': 16, 'inhouse-wrapper': 64}
weakest: raw-anthropic
One last thing before we move on. Same surface as a write step — but the lesson doesn't complete until this passes.
Final drill for the mindset lesson. Write triage_harnesses(harnesses)
that scores five harness configurations and returns a dict:
scores: dict mapping each harnessname→ its 0-100 score (insertion order preserved)weakest: the name of the harness MOST likely to fail first (lowest score). On a tie, return the FIRST one in input order.
Reuse the six-piece scoring from the previous drill:
- Each present piece (
config,tools,infra,orchestration,hooks,observability) adds 16. - All six present → 100.
Five harnesses run for you. Expected output:
scores: {'claude-code-pro': 100, 'cursor-default': 64, 'aider-basic': 32, 'raw-anthropic': 16, 'inhouse-wrapper': 64}
weakest: raw-anthropic
this step needs the editor
on desktop today; in the app (coming soon). save your spot and we'll bring you back here when you're ready.