Observability instrumentation decomposition
You're adding structured logging, metrics, and distributed tracing to an existing Python microservice and want an AI agent to do most of the instrumentation. How do you break this into pieces for the agent, what do you keep versus delegate, and where do you put human checkpoints?
Implement
find_telemetry_violations(kinds: list[str], names: list[str], cardinalities: list[int], max_label_cardinality: int) → list[str]Examples
in
[["log","label","label"],["request_id","route","user_id"],[100000,12,50000],100]out["user_id"]in
[["log","label"],["auth_token","status_code"],[3,7],100]out["auth_token"]in
[["label","label"],["region","customer_email"],[4,3],1000]out["customer_email"]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.