Question
Your team maintains firmware-adjacent C++ that frames and parses a binary telecom protocol over a serial link — length-prefixed messages, CRC, and strict byte alignment. A colleague suggests having an AI agent rewrite the parser to be cleaner. When would you NOT lean on the agent here, and what failure modes make it the wrong tool for the load-bearing parts?
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.