Ship or hold unreviewed code
It's 5pm before a launch freeze. An AI agent just produced a 400-line TypeScript change that wires a new feature flag through your auth middleware, and it builds and passes the smoke tests. Your lead says ship it now, unreviewed, because the window closes in 20 minutes. Walk through how you decide what to do — and where you'd draw the line between shipping it and holding it.
Implement
freeze_ship_decision(lines_changed: int, touches_auth: bool, flag_defaults_off: bool, minutes_left: int, already_reviewed: bool) → strExamples
in
[400,true,false,20,false]out"triage_targeted_review"in
[400,true,false,5,false]out"hold_until_after_freeze"in
[12,false,false,5,false]out"ship_now"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.