Question
Your team owns a payments service in Go: an HTTP API layer, a core ledger/double-entry module, a fraud-scoring service, a pile of glue (CSV importers, internal admin tooling), and the test suite. Engineering leadership wants a one-page policy declaring which parts of THIS codebase AI agents may write freely, which require a human author with AI as assistant, and which are off-limits to agent generation entirely. Draw those lines for these five areas and defend the boundary you'd be most criticized for.
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.