Back to library
Agents
Agent
everyone

Customer Research Synthesizer Agent

An autonomous Claude agent that ingests interview transcripts and returns a themed research readout with quotes and confidence scores.

Owner · Priya RameshUpdated · Jun 2, 2026Contact · priya@cabana.team

Overview

What it is

A long-running Claude agent (Sonnet 4.5) configured with a system prompt, a transcript-loading tool, and a quote-extraction tool. It iterates over a batch of transcripts, clusters themes, pulls verbatim quotes, and flags low-confidence findings before producing a final readout.

When to use it

When you have 10+ transcripts and want a hands-off synthesis run rather than an interactive Claude chat. Best for end-of-cycle research reviews.

Who it’s for

Researchers and PMs comfortable kicking off an agent run and reviewing the output.

Expected output

A markdown readout with: themes (ranked by frequency), supporting quotes (with transcript IDs), confidence per theme, surprises, and recommended follow-ups.

Setup instructions

  1. Open the Cabana Agents workspace in Claude.
  2. Duplicate the ‘Research Synthesizer’ agent template.
  3. Paste the system prompt from research-synthesizer.system.md.
  4. Connect the transcript-loader tool (points at the Research Drive folder).
  5. Run with a folder ID as input.

Usage

Good inputs

  • A Drive folder of cleaned transcripts (one per interview).
  • A 2–3 sentence research question.
  • Optional: prior synthesis to compare against.

Example prompts

  • Synthesize all transcripts in folder 2026-Q2-onboarding against the question ‘where do new members drop off in week 1?’

Expected outputs

  • A markdown readout (~2 pages) with themes, quotes, confidence, and follow-ups.

Tips & limitations

  • Always review low-confidence themes manually — the agent flags but doesn’t resolve them.
  • Cap batches at ~25 transcripts per run for best coherence.
  • Save the run ID so you can re-open the trace.

Tags

#agent
#claude
#research
#synthesis