Workspace PDF export decomposition
Product wants a full 'export workspace to PDF' feature: a button in the React app, a TypeScript backend endpoint that renders the workspace, queuing for large exports, and a download link emailed when ready. How do you decompose this for an AI agent into delegatable chunks with the right human checkpoints, rather than asking it to build the whole thing in one shot?
Implement
plan_export_jobs(request_keys: list[str], page_counts: list[int], in_flight_keys: list[str], max_pages: int) → list[str]Examples
in
[["ws1:u1","ws1:u1","ws2:u1"],[10,10,5],[],100]out["created","joined","created"]in
[["ws9:u2"],[500],[],100]out["too_large"]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 18 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.