Question
You're about to ask an AI agent to write the test suite for a new rate limiter (token-bucket: capacity, refill rate, per-key buckets) in Rust. You know that if you just say 'write thorough tests,' you'll get happy-path tests pinned to whatever the implementation happens to do. Write the prompt/spec you'd give the agent so the tests verify the real contract — and name the one thing a vague prompt gets most wrong here.
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.