Question
You're using an AI agent to build a feature in a TypeScript/React app: a CSV export button that streams a filtered table to a downloadable file. Sequence the build so each step is independently verifiable before the next, rather than asking the agent for the whole feature at once. Explain why your ordering makes each step checkable in isolation.
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.