Question
You use an AI agent across very different surfaces in a week: a throwaway data-analysis notebook, a Bash deploy script that runs as root on every production host, a React component's loading spinner, and a SQL migration that drops a column. Rather than reviewing everything with the same intensity, describe how you'd set a personal verification bar for each — and the principle that decides where the bar goes.
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.