Question
Your team is building a field-service mobile web app used by technicians in basements, elevators, and rural sites with intermittent connectivity. A junior used an AI agent to build the 'submit job report' form and it works flawlessly in the office. You're reviewing the spec, not the code. What does an AI-generated happy-path form fundamentally not account for here, and what would you add to the prompt/spec to get it right?
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.