Question
You're using an AI agent to generate a parser for a proprietary telecom signaling protocol (a vendor extension of Diameter) that exists only in a 200-page PDF spec and a handful of internal example captures. Generic prompts produce parsers that match the *standard* Diameter layout and silently mis-handle your vendor's extension AVPs. How do you supply context so the agent builds the right parser, and what's the core risk?
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.