Synthesize interview transcripts and PDFs for research
Claude Code is pointed at transcripts and PDFs to produce theme summaries, evidence tables and annotated bibliographies; a UX researcher runs 50-transcript studies this way.
Done withClaude Code
- What they did
- Transcripts go in one folder, one file per interview with consistent names, plus a CLAUDE.md holding research questions, a codebook and a rule to quote only verbatim text with file names. Claude codes them in batches of 5 to 8, or via parallel subagents, and writes themes.md and evidence tables. PDFs go in a papers folder for the bibliography. Claude then searches each quote in its source file.
- How it went
- The guide says one typed question replaces an hour of Ctrl+F, and Else van der Berg runs 50-transcript studies this way. Timing figures are illustrative, not benchmarked. One audit found 7.7% of supposedly verbatim quotes missing from sources.
- Worth knowing
- Pin the codebook before launching parallel agents, or you get incompatible theme lists. Always run the quote verification pass, and de-identify transcripts, since file contents are sent to Anthropic.
Try it yourself with Claude Code
Read all the interview transcripts and PDFs in [folder path] for my study on [research question]. Produce a theme summary, an evidence table with a quote and source file for each theme, and an annotated bibliography. Mark any theme supported by fewer than [number] sources as tentative, and save everything as separate files in a new output folder.
Source: ccforeveryone.com · Undated
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
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.
Run content research and sponsor outreach with Claude computer use
The author tested Claude computer use in Cowork and Claude Code over two days on six workflows including research, sponsor outreach and product listings.
Build a 2D platformer game without coding
A content creator with no coding experience used Claude Code to build a black-and-white wave-combat platformer in HTML canvas and played it live.
- Custom agent
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.
Automate a weekly arXiv paper triage
A weekly Codex automation searches arXiv for keywords, logs new papers to a CSV, sorts them into keep/skim/drop buckets and can check claims against Zotero.
Catalog and summarize papers dropped into Drive
An n8n workflow extracts metadata from new PDFs, finds related papers on Semantic Scholar and PubMed, builds an APA citation, logs to Sheets and creates a Notion summary.