Export to PDF service
You're building an export-to-PDF service in Node/TypeScript with an AI agent: users export reports (tables, charts, page breaks) to a downloadable PDF, generated server-side and potentially large/concurrent. Describe the build plan: library choice (headless-Chromium vs. a PDF DSL like PDFKit vs. wkhtmltopdf), how you sequence it, the resource/concurrency controls, and acceptance criteria. What does a careless 'generate a PDF from this HTML' prompt get wrong in production?
admit_render_requests(arrive_ms: list[int], cost_ms: list[int], pool_size: int, timeout_ms: int) → list[str][[0,0,0],[100,100,100],2,1000]out["done@100","done@100","done@200"][[0,0],[50,9000],1,2000]out["done@50","timeout@2050"]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 & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.