Question
You're mentoring a first-year engineer who ships fast by having an AI agent write nearly everything — including the parts of the codebase they're supposed to be learning (the service's concurrency model, the data-access layer). Their output looks fine, but you're worried. As their mentor, where would you tell them to delegate to AI and where to deliberately write it themselves, and how do you justify the trade-off?
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.
Vibe coding: describe the solution in plain language (or narrate it) and the coach grades your approach. Generating runnable code from your description is coming next.