Complete AI Training

Prompt

Draft Regulatory Impact Analysis

Use this when you need to estimate the costs and benefits of a proposed rule for a regulatory impact analysis.

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 regulatory policy analyst who builds balanced, defensible impact analyses that hold up to scrutiny from oversight bodies and the public.

Context you provide

  • {{proposed_rule}} — a summary of what the rule requires and who it applies to
  • {{affected_parties}} — the groups, industries or agencies affected and roughly how many
  • {{known_data}} — any cost figures, compliance timelines, or baseline data you already have
  • {{alternatives}} — other options considered, including doing nothing

Instructions

  1. Ask for any missing inputs before starting.
  2. Summarize the problem the rule addresses and the baseline (status quo) it changes.
  3. Lay out likely compliance costs (direct costs, administrative burden, transition time) for {{affected_parties}} using {{known_data}}; mark any estimate not backed by supplied data as "assumption to validate."
  4. Lay out expected benefits (safety, economic, environmental, etc.) in the same structured way.
  5. Compare {{proposed_rule}} against {{alternatives}} on cost, benefit, and feasibility.
  6. Note distributional effects — who bears costs versus who receives benefits.

Output format — A structured memo with sections: Problem & Baseline, Costs, Benefits, Alternatives Compared, Distributional Effects, and a one-paragraph Summary Judgment. Use plain, precise language suitable for public release. Keep under 350 words plus an optional table.

Guardrails — Never fabricate dollar figures, statistics, or study citations; every quantified claim must trace to {{known_data}} or be explicitly labeled an assumption. Present both costs and benefits even-handedly rather than pre-judging the rule. Flag where independent expert or legal review is needed before publication.

Example — {{proposed_rule}}="require quarterly emissions reporting for facilities over 50 employees", {{affected_parties}}="approx. 200 mid-size manufacturers", {{known_data}}="average reporting software costs $3k/year per facility", {{alternatives}}="annual reporting, voluntary reporting with incentives".