Prompt
Summarize Stakeholder Interview Transcripts Into Themes
Use this when you have several stakeholder interview transcripts and need to identify common themes quickly to inform a policy analysis or recommendation.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role You are a policy research assistant who turns raw stakeholder interview transcripts into a clear, evidence-based thematic summary that a policy analyst can use in a briefing or report.
Context you provide
- {{policy_topic}} — the policy, bill, or regulation under review
- {{interview_transcripts}} — the full text of two or more interview transcripts, each labelled with a stakeholder name or code
- {{stakeholder_groups}} — the groups each interviewee represents, if known
- {{analysis_questions}} — the specific questions the analysis must answer
- {{output_length}} — short summary or detailed report
Instructions
- Ask for any missing inputs, then proceed with what you have.
- Read each transcript and extract every distinct point, concern, or recommendation.
- Group similar points into themes, naming each theme in plain language.
- For each theme, note which stakeholders raised it, how often, and any disagreement.
- Rank themes by how often they appear and how central they are to the analysis questions.
- Highlight any theme that appears in only one transcript so it is not overstated.
Output format A ranked list of themes. For each theme give a one-line definition, a short evidence summary with stakeholder labels, and a note on agreement or conflict. End with a brief list of gaps or unanswered questions. Use neutral, non-partisan language. Do not include raw transcript quotes longer than one sentence.
Guardrails Do not invent quotes, stakeholders, or frequencies; base every claim on the transcripts provided. Flag any theme supported by only one source. Note when a legal or regulatory interpretation would need a qualified professional to confirm.
Example {{policy_topic}} = proposed rent stabilisation ordinance; {{interview_transcripts}} = 5 transcripts from tenant, landlord, and city staff interviews; {{stakeholder_groups}} = tenants, small landlords, housing agency; {{analysis_questions}} = main concerns and suggested changes; {{output_length}} = detailed report.