Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for policy makers

International Policy Comparison Agent

A fair comparison of how similar jurisdictions handled a policy issue and what changed

ResearchGovernment
See how it worksGet access
International Policy Comparison Agent: what goes in, what the agent does and what you get

What it does

Officials often ask what other countries or states did about a problem and what happened next. Answering well takes days of digging through laws and data. This agent first sets comparison criteria with the official, then finds jurisdictions that adopted similar policies and collects their laws, start dates and outcome data from official and international sources. It checks whether outcomes are measured the same way in each place. If not, it adjusts to a common measure or flags the gap and searches for better data. It also notes context that limits transfer, such as a different health or tax system, and shows trends from before each policy began. The official decides which lessons apply. Edge case: if outcomes improved in a country before its policy started, the agent notes the policy may not be the cause.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueApprovedNo 1 STARTS WHEN Official asks for a comparison 2 DOES Set comparison criteria with the official 3 USES A TOOL Find jurisdictions that adopted similar policies 4 USES A TOOL Collect laws, dates and outcome data 5 CHECKS THE RESULT Are outcomes measured the same way across places? If not: adjust to a common measure or flag the gap andsearch for better data. Back to step 4. 6 DOES Note trends before the policy and context limits 7 YOU APPROVE Official reviews findings before sharing 8 RESULT Comparison table and memo
Read the steps as a list
  1. Official asks for a comparison
  2. Set comparison criteria with the official
  3. Find jurisdictions that adopted similar policies
  4. Collect laws, dates and outcome data
  5. Are outcomes measured the same way across places?If not: adjust to a common measure or flag the gap and search for better data. Back to step 4.
  6. Note trends before the policy and context limits
  7. Official reviews findings before sharingThe agent waits here for your OK.
  8. Comparison table and memo

How it decides

Jurisdictions are included only if they match on the agreed criteria. Outcomes are compared only when measured in the same way or adjusted.

  • Include only jurisdictions that meet the criteria
  • Pre-policy trends are always shown
  • Context differences are listed for each case

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Comparison criteria
  • Number of jurisdictions (default 4 to 6)
  • Outcome measures to compare
  • Languages to search

What keeps you in control

It always asks you first

  • Official approves before the comparison is shared

Hard limits

  • Uses official or peer-reviewed sources only
  • Does not claim causation

It stops when

  • Done: at least three comparable cases analyzed
  • Stop: fewer than two comparable cases exist

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensFor sugary drink taxes, the agent selected 6 countries. Mexico and the UK reported purchases, but France reported consumption surveys, so the measurement check failed. It went back and pulled purchase data for France from the national statistics office. It also noted that UK sugar content was already falling before the levy started. The deputy minister reviewed the table and approved sharing it with the committee.

More agents for policy makers

Reporting · Creating

Public Consultation Theme Evidence Agent

A consultation summary that fairly reflects every view, with traceable evidence.

7 steps1 check2 jobs
Reporting · Government

Campaign Promise Delivery Tracker Agent

A sourced status table for every promise that the official can publish with confidence

10 steps2 checks4 jobs
Analysis · Quality control

Fiscal Note Review Agent

A memo that shows whether the fiscal note's totals can be reproduced, which assumptions drive them and a range

10 steps2 checks3 jobs
Monitoring · Risk management

Expiring Law and Sunset Watch Agent

No sunset date arrives without an up-to-date briefing and a known reauthorization status

10 steps2 checks4 jobs