OAuth2 session management decomposition
Your service needs to add OAuth2 'sign in with provider X' plus session management to a Go backend, and you want an AI agent to build most of it. How do you decompose the work, which parts do you keep versus delegate, and where do human checkpoints belong before this touches production?
Implement
classify_oauth_tasks(tasks: list[str]) → list[str]Examples
in
[["Generate and check the OAuth2 state parameter","Scaffold the HTTP handler for the callback route","Verify the ID token signature against provider JWKS"]]out["own","delegate","own"]in
[["Add PKCE code challenge to the authorization request","Style the sign in button"]]out["own","delegate"]in
[["Write a stateless health check endpoint"]]out["delegate"]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.