What aged: the 2023 prompting tricks that became 2026 traps — step 8 of 8

Final drill. Synthesize this lesson into one function: audit_prompts(techniques) that takes a list of technique dicts and returns a dict with TWO keys:

• verdicts: a dict mapping technique name → verdict string
• counts: a dict mapping each verdict to how many techniques got that verdict. Include all four verdicts as keys even if the count is zero.

Each technique dict has three fields: name, year_introduced, model_native_in (which may be None).

Use the same verdict rules as step 07:

• model_native_in is None → "still useful"
• model_native_in <= 2025 and name in reasoning set → "redundant"
• model_native_in <= 2025 and name NOT in reasoning set → "counterproductive"
• otherwise → "context-dependent"

Reasoning set: {"chain-of-thought", "think-step-by-step", "self-critique"}.

Five techniques demoed. Expected output:

verdicts: {'chain-of-thought': 'redundant', 'few-shot-examples': 'still useful', 'structured-output-schema': 'counterproductive', 'self-critique': 'redundant', 'multi-tool-orchestration': 'context-dependent'}
counts: {'still useful': 1, 'redundant': 2, 'counterproductive': 1, 'context-dependent': 1}