Skip to main content
Original: Simon Willison · 16/03/2026

​
Summary

Simon Willison’s workshop at NICAR 2026 focused on using coding agents like Claude Code and OpenAI Codex for data analysis, aimed at data journalists.

​
Key Insights

“Here’s the handout I prepared for my NICAR 2026 workshop ‘Coding agents for data analysis’.” — Introduction to the workshop and its purpose.
“Participants ended up burning $23 of Codex tokens.” — Highlighting the practical use of OpenAI Codex during the workshop.
“Material aimed at data journalists is equally applicable to anyone else with data to explore.” — Emphasizing the broader relevance of the workshop content.

​
Topics

​
Full Article

16th March 2026 - Link Blog Coding agents for data analysis. Here’s the handout I prepared for my NICAR 2026 workshop “Coding agents for data analysis” - a three hour session aimed at data journalists demonstrating ways that tools like Claude Code and OpenAI Codex can be used to explore, analyze and clean data. Here’s the table of contents: Coding agents Warmup: ChatGPT and Claude Setup Claude Code and Codex Asking questions against a database Exploring data with agents Cleaning data: decoding neighborhood codes Creating visualizations with agents Scraping data with agents I ran the workshop using GitHub Codespaces and OpenAI Codex, since it was easy (and inexpensive) to distribute a budget-restricted API key for Codex that attendees could use during the class. Participants ended up burning $23 of Codex tokens. The exercises all used Python and SQLite and some of them used Datasette. One highlight of the workshop was when we started running Datasette such that it served static content from a viz/ folder, then had Claude Code start vibe coding new interactive visualizations directly in that folder. Here’s a heat map it created for my trees database using Leaflet and Leaflet.heat, source code here. I designed the handout to also be useful for people who weren’t able to attend the session in person. As is usually the case, material aimed at data journalists is equally applicable to anyone else with data to explore.

Use subagents and custom agents in Codex

Simon Willison · how-to · 65% similar

[AINews] NVIDIA GTC: Jensen goes hard on OpenClaw, Vera CPU, and announces $1T sales backlog in 2027

Swyx · explanation · 64% similar

An AI agent coding skeptic tries AI agent coding, in excessive detail

Simon Willison · explanation · 64% similar
Originally published at https://simonwillison.net/2026/Mar/16/coding-agents-for-data-analysis/#atom-everything.