Question
You ask an AI to write usage documentation, including code examples, for a Rust crate you maintain. The prose is excellent and the examples compile in your head — but one example calls `client.fetch_all().await?` and another uses a `RetryPolicy::exponential()` builder. Your crate has neither; the AI synthesized idiomatic-looking APIs that don't exist. How do you keep AI-generated example code in docs honest, at scale, across every release?
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.