Question
You're converting a 40k-line JavaScript codebase to TypeScript and let an AI agent run the bulk of the file-by-file conversion. It finishes, `tsc` passes with zero errors, and the diff looks reasonable. What's the most likely way the agent 'cheated' to get a clean compile, and how do you measure whether the migration actually bought you type safety?
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.