Coding agents for data analysis

A three-hour workshop presented by Simon Willison at NICAR 2026.

Coding agents such as Claude Code and OpenAI Codex are mainly marketed at developers, but they’re actually applicable to a much wider array of problems, including data analysis, data cleaning, web scraping and other tasks commonly faced by data journalists.

In this session, you’ll learn how to apply these tools to both simple and ambitious data reporting projects. You’ll go away with a very powerful new tool for collecting, exploring, analyzing and presenting data.

• Coding agents
  • What’s an agent?
  • What’s a coding agent?
  • ChatGPT and Claude as coding agents
  • The tools we’ll use
• Warmup: ChatGPT and Claude
• Setup Claude Code and Codex
  • Using Codespaces
  • YOLO mode
  • Local setup
  • Installing Datasette
• Asking questions against a database
  • Simple example: San Francisco street trees
  • Bring your own data
• Exploring data with agents
  • FEC campaign finance data
  • Setting up dclient
  • Using Showboat
  • Open-ended exploration
  • Push for more
  • Evaluating the results
• Cleaning data: decoding neighborhood codes
  • Research the codes
  • Verify the results
• Creating visualizations with agents
  • Python visualizations
  • JavaScript visualizations
• Scraping data with agents
  • Browser automation with rodney
  • Exercise: ProPublica financial disclosures
  • Deciphering the underlying data