Question
Your team adopted AI agents organically, and now everyone prompts differently: some paste huge context and get good results, others one-line their requests and merge whatever comes back, and the codebase is drifting toward inconsistent patterns because each person's agent invents its own conventions. You're asked to onboard a new teammate and, while you're at it, establish a shared AI workflow. What concretely do you put in place so the team gets consistent, reviewable output instead of a different agent personality per engineer?
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.