Search as you type
You're building a search-as-you-type box in React + TypeScript against a `/search?q=` API, greenfield, and handing it to an AI agent. Spell out the build plan: the client-side debounce/cancellation strategy, what the API contract needs, the acceptance criteria, and the review gates. What does a careless 'add a live search box' prompt get wrong about correctness and load?
Implement
plan_search_requests(texts: list[str], times: list[int], debounce_ms: int, min_query_length: int) → list[str]Examples
in
[["c","ca","cat"],[0,80,160],250,2]out["cat"]in
[["c","ca","cat"],[0,300,600],250,2]out["ca","cat"]What a strong answer looks like
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.
0:00 of about 20 min
Vibe & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.
Which questions mattered is sealed until you submit. Telling you now would just be handing over the edge cases.
Run or narrate your approach, then ask the coach.