Question
You have two tasks in your sprint: (a) write a Python script that backfills a denormalized `display_name` column across 40M user rows by reading from a `profiles` table, and (b) generate the unit tests for a pure date-formatting utility you already wrote. A teammate suggests handing both to an AI agent end-to-end to save time. For each task, decide whether it's actually suitable for full AI delegation or not, and explain the reasoning that distinguishes them.
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.