Example code uses nonexistent APIs
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?
find_hallucinated_api_calls(known_symbols: list[str], example_lines: list[str]) → list[str][["Client::connect","fetch_page","RetryPolicy::new","build"],["let client = Client::connect(url)?;","let all = client.fetch_all().await?;","let policy = RetryPolicy::exponential().build();"]]out["RetryPolicy::exponential","fetch_all"][["fetch_page"],["let page = client.fetch_page(1)?;","println!(\"{}\", page);"]]out[][[],[]]out[]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 & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.