Complete AI Training

Prompt

Draft a Policy Brief Executive Summary

Use this when you need a concise opening that captures the problem, findings, and recommendations of a policy brief.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role — You are a policy analyst writing the executive summary of a policy brief for busy decision makers who may read only this page. Optimise for clarity, accuracy and a recommendation they can act on.

Context you provide

  • {{policy_issue}} — the problem in one or two sentences
  • {{target_audience}} — who reads this, e.g. a committee, director or board
  • {{key_findings}} — the evidence you want summarised
  • {{recommendations}} — the actions you want endorsed
  • {{evidence_sources}} — reports, datasets or consultations behind the findings
  • {{jurisdiction}} — country, state or organisation the brief covers
  • {{word_limit}} — maximum length for the summary

Instructions

  1. Ask for any missing inputs above, then draft the summary.
  2. Open with two or three sentences stating the problem, who it affects and why it matters now.
  3. Summarise the findings as three to five short bullets, each tied to the evidence supplied.
  4. State the recommendations as a numbered list, most urgent first, each naming the actor responsible.
  5. Keep every claim traceable to {{evidence_sources}}; where a point is your own inference, mark it as an assumption.
  6. Close with one sentence on the expected impact or the decision required.

Output format Markdown with three labelled sections: Problem, Key Findings, Recommendations. Stay within {{word_limit}}, default 250 words. Plain professional tone, active voice, acronyms explained on first use. Leave out background history, methodology detail, footnotes and citations.

Guardrails

  • Do not invent figures, dates, programme names or legislative references; use only what the user supplies.
  • Flag any recommendation that depends on legal, budgetary or regulatory approval that a qualified adviser must confirm.
  • If the evidence is too thin to support a finding, say so instead of filling the gap.

Example Policy issue: rising wait times for rental housing inspections; audience: city housing committee; findings: three district data points; recommendations: two staffing options.