CSV to Postgres importer
Greenfield Go service: an AI agent will build a CSV-to-Postgres importer where admins upload customer records (up to ~2M rows), and you need per-row validation, a dry-run preview, and a partial-failure report rather than all-or-nothing. Describe how you'd direct the agent — streaming vs. load-all, the validation strategy, transaction boundaries, and acceptance criteria. Where does a one-shot 'import this CSV' prompt fail at this scale?
build_import_report(rows: list[str], chunk_size: int) → list[str][["ada@example.com,Ada,36","bob@example.com,Bob,41","carl@example.com,Carl,29"],2]out["imported=3 skipped=0 chunks=2"][["ada@example.com,Ada,36","no-at-sign,Bob,41","ADA@example.com,Ada,36","carl@example.com,,29"],5]out["imported=1 skipped=3 chunks=1","row=2 error=invalid_email","row=3 error=duplicate_email","row=4 error=missing_name"]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.