AI Services Market › Use cases › Research & Knowledge
Research & KnowledgeDone with Claude Code Oct 26, 2026
Fetch and analyze economic data for research
An economist used Claude Code to find Census homeownership data, clean it and chart it, and to scrape SEC 10-K risk factors into a DuckDB database showing tariff-risk changes. · Oct 26, 2026
- What They Did
- In a webinar series, Paul Goldsmith-Pinkham ran Claude Code, a terminal-based assistant, on two tasks. For homeownership, it found the Census data, dealt with scraping problems, cleaned the spreadsheets and wrote the scripts to plot it. For the second, it scraped SEC EDGAR 10-K filings, extracted risk factors and built a DuckDB database. He planned and iterated on the results.
- How It Went
- The tariff-risk database showed tariff-related disclosure becoming more frequent and more specific in recent years. The source says messy filings became usable research data in just a few minutes.
- Worth Knowing
- The source stresses planning first and iterating on results with Claude Code. Detailed step-by-step notes are in his Substack posts for episodes 2 and 3.
Try it yourself with Claude Code
I'm researching [economic question, e.g. how homeownership rates changed by age group]. Find the right public data from [source, e.g. Census Bureau or SEC filings], download it, clean it, and store it in a DuckDB database in this folder. Then produce a chart and a short written summary of what the data shows, with the source links and any gaps or caveats noted. Stop when the chart, database and summary are saved.
Do this with a skill.
These AI Services Market playbooks do this exact job.