Question
Your team keeps shipping AI-generated UI components that pass design review but fail accessibility audits weeks later (missing labels, no keyboard support, color-only state). Rather than fixing each one after the fact, you want to change how the team prompts and verifies. As a staff engineer, what would you put in place so accessibility is part of the generation loop, not a cleanup pass?
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.