Agent-written test trust
Your agent implemented a feature and also wrote the tests for it, and everything is green — including the tests it authored. Your teammate says 'tests pass, ship it.' You're uneasy because the same model wrote both the code and its checks. How do you calibrate how much to trust this, and what do you actually do before merging?
Implement
find_surviving_mutants(mutant_ids: list[str], killing_test_counts: list[int]) → list[str]Examples
in
[["m1","m2","m3"],[2,0,1]]out["m2"]in
[["off_by_one","null_input"],[0,0]]out["null_input","off_by_one"]in
[[],[]]out[]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 15 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.