Question
An AI assistant wrote you a Python function `days_between(start, end)` that returns the number of days between two date strings like '2026-01-01'. It compiled and returned a number on your first test, '2026-01-01' to '2026-01-10', giving 9. You're ready to call it done. Why is one passing example not enough here, and what specific extra inputs would you run before trusting it?
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.