Recipes / Data & reports
CodexWorkflowData & reports

Explore, clean and chart a dataset with a coding agent

A workshop handout for data journalists: use Claude Code or Codex to ask questions of a database, clean messy codes, build visualizations and scrape data.

From Simon Willison · Blog · Mar 2026

Setup time30 min
CostPay-per-token (the workshop spent $23 total)
RunsPer dataset
NeedsCodex or Claude Code, Python, SQLite, Datasette (optional)
Last updated2026-10-17

What the source did

  • Ran a 3-hour workshop on GitHub Codespaces with a budget-restricted Codex key.
  • Had attendees query SQLite, decode neighborhood codes and scrape with agents.
  • Served a viz/ folder through Datasette and had Claude Code build an interactive Leaflet heat map there.

Summary written by Agent Cookbook. See the original for the full context.

Read their guide

Made and published by Simon Willison. Start here; it is their original, not ours.

Approval rule

🛡
The agent writes to a copy; the original data file stays read-only.

Set it up

  1. Put the data in a fresh folder or Codespace.
  2. Set a spending cap on the API key if you use one.
  3. Work through the handout's exercises on your own data and check the SQL yourself.
  4. Open the viz file locally.

Common failures

⚠
  • Agents state numbers confidently; always ask for the query behind a figure.
  • Scraping steps may break site terms. Check before running.

Variations

  • Point Datasette at viz/ so new charts show up live.
  • Use the same flow for spreadsheets exported to CSV.

Get the 10 best agent setups. Free.

Plus new recipes every week. One email, no spam.

Unsubscribe anytime. Privacy

Related recipes

Get their template ↗Read original ↗