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.
Done withClaude Code
- 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.
Want help getting this working? Join the Vibe Coding Academy ↗ Run by Alex Finn, who also runs this site.
Source: economics.princeton.edu · Oct 26, 2026 · Submitted by from search gap: 学术
Related use cases
Turn tickets into merged pull requests
Pulls tasks from GitHub Issues or Linear, then runs Claude Code or Codex in isolated Kubernetes pods to carry each one through to a PR.
Build prospect lists and cold emails from the web
Claude Code driving the author's logged-in Chrome read seed pages and LinkedIn profiles to find 25-30 sourced prospects; about 20 emails sent drew 7 replies.
Summarize non-obvious methods file by file in a paper project
A commenter had Claude Code write file-by-file summaries of non-obvious methods in a research project, then reviewed them to keep track of the work.
Run persistent financial research with an agent
LangAlpha is a Claude Code-style agent for investing research that keeps persistent workspaces and memory so analysis such as models and comps can be updated across sessions.
Custom agent
Use Cursor for academic paper writing with citations
Forum users write papers in markdown with Zotero citations and a bibtex file for Cursor to pick references from, converting to Word with pandoc.
Investigate papers overnight with a bot research team
Grok Bot roles read new papers and extract claims, rerun analyses, and scan sources, working overnight to produce briefs.
Get 5 like this every morning
The best things people got an AI agent to do, each with the prompt to try it.