Password reset flow spec
You're delegating a password-reset flow to an AI agent (email a reset link, user sets a new password) in a Node app. Write the spec so the agent produces something secure. What security constraints and acceptance criteria must be explicit, and what does a generic 'add forgot-password' prompt get unsafe?
Implement
reset_token_status(token_hashes: list[str], used_flags: list[bool], expiry_times: list[str], presented_hash: str, now_time: str) → strExamples
in
[["h_a","h_b"],[false,false],["2026-01-01T10:00:00Z","2026-01-01T10:00:00Z"],"h_a","2026-01-01T09:00:00Z"]out"accepted"in
[["h_a","h_b"],[false,false],["2026-01-01T10:00:00Z","2026-01-01T10:00:00Z"],"h_b","2026-01-01T10:00:00Z"]out"expired"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 22 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.