UseAgentBEFORE YOU RUN
Know the job and the reviewer.
This playbook is for product leaders, founders, and researchers reviewing qualitative feedback.
TARGET OUTCOME
A decision-ready synthesis that keeps evidence tied to participants and distinguishes recurring themes from isolated comments.
Bring these inputs
Better source material makes the result easier to review and safer to reuse.
- Interview notes or transcripts
- Participant labels and segments
- Research questions
- Existing hypotheses to test
COPYABLE STARTER
Start with this prompt.
Replace bracketed details, attach the source material, and keep the limits until your team has reviewed a few runs.
Synthesize these customer interviews against the research questions. For each theme, show supporting participants, counterexamples, representative excerpts, and confidence based on this sample only. Separate observed behavior, stated preference, and our interpretation. End with decisions this evidence informs and questions it cannot answer.
THE PLAYBOOK
Move from context to a reviewed result.
- 01
Label the sample
Use stable participant IDs and relevant segments so themes can be traced without exposing unnecessary personal information.
- 02
Code evidence first
Extract needs, behavior, friction, workarounds, and desired outcomes before writing a narrative.
- 03
Preserve disagreement
Ask for counterexamples and segment differences. A clean story can hide useful product signal.
- 04
Map to decisions
Connect evidence to open product questions while stating what the sample cannot establish.
DELIVERABLES
What the run should produce
- Theme matrix
- Evidence excerpts
- Counterexample list
- Decision and research questions
HUMAN REVIEW
Check this before it leaves the team
- Every theme traces to participants
- Quotes retain their meaning
- Sample limits are stated
- Interpretation is labeled separately
Keep exploring this workflow