Question
You want an in-memory memoization decorator in Python, `@memoize(maxsize, ttl)`, that caches a pure function's results with a size cap and a time-to-live. You'll ask an AI agent to write it. Draft the prompt/spec — constraints, edge cases, acceptance criteria — for a first-try-correct result. What does a lazy prompt ("add a caching decorator with a TTL") get wrong?
Treat the AI’s output as a draft to verify, not an answer to trust. Name the specific flaw and the input that triggers it, say how you’d catch it — tests, edge cases, reading critically — and how you’d re-prompt or decompose to get it right.
Vibe coding: describe the solution in plain language (or narrate it) and the coach grades your approach. Generating runnable code from your description is coming next.