Question
Greenfield: an AI agent will build a real-time chat feature in TypeScript — a WebSocket server (Node/ws) plus a browser client — supporting rooms, presence, and message history. Describe how you'd sequence and scope the build with the agent: the connection lifecycle, reconnection/backpressure handling, message ordering/delivery, and acceptance criteria. What does a careless 'build a WebSocket chat' prompt get wrong once it leaves localhost?
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.