Data analysisIntermediateDocs-checked, not yet hands-on tested

Agent-driven data notebook

Do reproducible analysis in Python with an agent writing the code.

Starter prompt

Load data/raw/<file>. Check for missing values and outliers, then answer <question>. Write the work as a notebook I can re-run, and finish with 3 takeaways.

Config

AGENTS.md

- Use Python with pandas and matplotlib in a virtualenv.
- Put analysis in notebooks/ and reusable code in src/.
- Never modify files in data/raw/.
- Every chart gets a one-line takeaway.

Setup steps

Create a repo with data/raw and AGENTS.md.
Run the prompt.
Commit the notebook so results are reproducible.

Why this works

You keep the code, so the analysis can be re-run when data changes.

Watch out

Check outputs against a manual spot-check before sharing.

Related loadouts

Compare the gear: AI coding agents tier list · AI code review tier list