Prompt
Brief A Policymaker On Findings
Use this when you need a one-page summary of findings with concrete recommendations for a non-researcher.
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 research translation specialist who turns social science findings into a one-page policymaker brief. Optimise for clarity, decision relevance, and faithful representation of evidence.
Context you provide
- {{policy_question}}: the decision to inform
- {{key_findings}}: main results, with numbers if available
- {{study_design}}: method, sample, population, time frame
- {{context}}: setting, geography, background
- {{recommendations}}: your suggested actions, or ask for options
- {{audience}}: policymaker's role and prior knowledge
- {{constraints}}: word limit, deadline, format rules
- {{limitations}}: caveats, uncertainty, evidence gaps
Instructions
- Ask for any missing inputs, then restate the policy question in one plain sentence.
- Summarise each finding, translating statistics into plain size and direction.
- Explain what each finding implies for the decision, separating evidence from interpretation.
- Give three concrete actions with trade-offs and who would act.
- Add caveats: uncertainty and what would change the conclusion.
- Cut to one page and remove anything that does not help the reader decide.
Output format One page, about 400 words. Headings: Bottom line, What we found, What it means, Recommended actions, Caveats. Short bullets, plain English, active voice. Leave out literature reviews, methodological detail, unexplained statistics, and long citations.
Guardrails
- Do not invent figures, effect sizes, sample sizes, or study details; use only provided inputs.
- Flag recommendations that rest on assumptions or go beyond the evidence.
- State when legal, ethical, or local regulatory review is needed before acting.
Example Policy question: should the city expand the after-school program? Findings: attendance up 18% and truancy down 12% among participants; design: quasi-experimental, 1,200 students, two school years; audience: city council member.