Question
Your team is adding a feature-flag system to a TypeScript monorepo: flags defined in a config, evaluated server-side and client-side, with per-user targeting rules and a kill switch. You want to use an AI agent for most of it. How do you decompose this into pieces for the agent, which parts do you delegate and which do you keep, and where do you insert human checkpoints before merging?
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.