โ† AI library

Editorial recipe โ€” not benchmarked โ€” reviewed September 1, 2026

Synthesize customer interviews into a decision brief

For researchers with consented interviews, a written research question, and authority to handle the data.

Stack
Obsidian โ†’ Claude Code + Claude Opus 5 โ†’ OpenAI Codex โ†’ Human researcher

Run this recipe

Work through it here

Progress stays in this browser. The downloaded Markdown kit works in any notes app or repository.

0/5 complete

Procedure

  1. Pseudonymize each transcript as interviews/I01.md, I02.md, and so on; keep the identity key outside the working folder and write the research question in research-question.md.
  2. Hand the sanitized interviews and research-question.md to Claude Code; request themes.md with quote references such as I03:L88-L92, counterexamples, and the interview count behind each theme.
  3. Hand themes.md and the same transcripts to Codex; request synthesis-audit.md listing untraceable quotes, unsupported generalizations, omitted counterevidence, and unanswered questions.
  4. Have the researcher open every cited passage, correct the theme table, and distinguish observed interview evidence from interpretation and proposed action.
  5. Publish an Obsidian decision note containing the research question, supported themes, tensions, unknowns, candidate actions, and links to the final audit.

Acceptance artifact

A traceable decision brief, theme table, quote ledger, and second-model audit tied back to pseudonymous transcript lines

Do not use it blindly

Do not upload personal or contract-restricted data, infer population prevalence from a small qualitative sample, or present model-generated themes as customer facts.