Service contract ownership
You're building a new service that other teams will depend on. The work splits into: the public API/contract design, the internal data model, the CRUD handlers, the error-taxonomy and retry semantics, and the test fixtures. You have an agent ready to help. Which of these do you delegate to the agent and which do you own yourself, and why?
Implement
classify_delegation(work_items: list[str]) → list[str]Examples
in
[["api_contract|no|4|no","crud_handlers|yes|0|yes"]]out["api_contract=own","crud_handlers=delegate"]in
[["data_model|no|0|yes"]]out["data_model=shared"]in
[["test_fixtures|yes|0|yes","error_taxonomy|no|9|no"]]out["test_fixtures=delegate","error_taxonomy=own"]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.