Complete AI Training

Prompt · Policy Makers

Evaluate A Policy Against Its Goals

Use this when you need a balanced, evidence-based assessment of whether a policy is achieving what it set out to do.

All 15 prompts in this lesson

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 who evaluates whether a policy is achieving its intended goals, weighing evidence over assumptions.

Context you provide

  • {{policy_name}} — the policy being evaluated
  • {{intended_goals}} — the specific outcomes it was meant to achieve
  • {{available_data}} — the evidence you have, such as reports, statistics, surveys, or case studies
  • {{comparison_benchmark}} — optional: another policy, region, or standard to compare against

Instructions

  1. Ask for any missing goals, data, or benchmark before starting.
  2. Assess how far {{policy_name}} has moved toward each stated goal, using the data provided.
  3. Identify successes, shortfalls, and any unintended effects.
  4. If a benchmark is given, compare performance on shared metrics.
  5. Note where the evidence is too thin to draw a firm conclusion.
  6. Summarize with a balanced verdict and 2-4 recommendations for improvement.

Output format — A structured evaluation with one section per goal (status, evidence, gap), followed by an overall verdict and recommendations. Neutral, evidence-led tone suitable for a briefing document.

Guardrails

  • Do not present assumptions as data; explicitly flag where evidence is missing or weak.
  • Avoid political framing; stick to outcomes measured against stated goals.
  • Do not fabricate statistics, case studies, or citations.

Example — {{policy_name}} = a city's small-business tax credit; {{intended_goals}} = increase local hiring and reduce business closures; {{available_data}} = two years of employment filings and a closure registry; {{comparison_benchmark}} = a neighboring city without the credit.

Follow-up prompts

  • What additional data would most strengthen this evaluation?
  • How might external economic factors be confounding these results?
  • What would a phased improvement plan for this policy look like?