AI-assisted ETL decomposition
You're building a nightly ETL pipeline that pulls events from several upstream sources, normalizes and joins them, and loads a warehouse table other teams query. You want an AI agent to build most of the pipeline in Python. How do you decompose it, what do you keep versus delegate, and where do human checkpoints belong?
Implement
dedupe_to_grain(events: list[str]) → list[str]Examples
in
[["acct7:1:250","acct3:2:100","acct7:2:275"]]out["acct3:2:100","acct7:2:275"]in
[["a:5:1","a:5:9"]]out["a:5:1"]in
[[]]out[]What a strong answer looks like
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.
0:00 of about 22 min
Vibe & agentic: describe the solution in plain language (or narrate it) and the coach grades your approach.
Which questions mattered is sealed until you submit. Telling you now would just be handing over the edge cases.
Run or narrate your approach, then ask the coach.