Question
You're asking an AI agent to generate a JavaScript regex that validates user-submitted email addresses on a public sign-up endpoint. Write the prompt/spec that gets a correct, safe pattern the first time — what constraints, edge cases, and acceptance criteria do you spell out, and what should the AI use instead of a hand-rolled mega-regex? Then state what a naive prompt like "write a regex to validate emails" would produce that's actually dangerous in production.
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.