Question
A customer uploads a CSV of up to 200k contact rows that you must import into Postgres. Write the spec you'd hand an AI agent to build the Python importer. What edge cases, constraints, and acceptance criteria must be in the spec for the result to survive real-world files — and what does a one-line 'parse the CSV and insert it' prompt silently get wrong?
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.