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

Public Consultation Theme Evidence Agent

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

ReportingCreatingQuality controlGovernment
See how it worksGet access
Public Consultation Theme Evidence Agent: what goes in, what the agent does and what you get

What it does

Public consultation summaries can drop minority views or over-count duplicate submissions. When a consultation closes, this agent groups submissions into themes, each backed by quotes from the submissions. It reviews ambiguous submissions more closely and applies duplicate rules openly, for example counting a form letter as a campaign with a stated number of signers. It then runs a coverage check of all positions. If a position, including a minority one, is missing from the summary, it revises the summary and reruns the check. The consultation lead approves the draft. Policy decisions and publication stay with people, and participants are never identified. Edge case: one submission supports and opposes parts of the plan, so it is counted under both themes.

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 Consultation closes 2 USES A TOOL Group submissions into themes 3 DOES Review ambiguous submissions 4 USES A TOOL Run a coverage check of all positions 5 CHECKS THE RESULT Are all positions, including minority ones,represented? If not: revise the summary. Back to step 3. 6 YOU APPROVE Consultation lead approves 7 RESULT Traceable consultation summary draft
Read the steps as a list
  1. Consultation closes
  2. Group submissions into themes
  3. Review ambiguous submissions
  4. Run a coverage check of all positions
  5. Are all positions, including minority ones, represented?If not: revise the summary. Back to step 3.
  6. Consultation lead approvesThe agent waits here for your OK.
  7. Traceable consultation summary draft

How it decides

It reviews themes with conflicting evidence more deeply and re-runs coverage after each revision.

  • Themes with conflicting evidence get a deeper review.
  • Duplicates are counted only under explicit, stated rules.
  • Every position found in submissions must appear in the summary.
  • Participants are never named.

Make it yours

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

  • Rules for counting duplicates and form letters
  • Smallest number of submissions that forms a theme (default 5)
  • Whether quotes appear in the summary
  • Who approves the summary
  • Output format (report or theme table)

What keeps you in control

It always asks you first

  • Policy decisions
  • Publication
  • Participant identification

Hard limits

  • No identification of participants.

It stops when

  • Done: coverage check passes.

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 happensA transit consultation closes with 1,240 submissions, including a 380-copy form letter counted as one campaign. The agent forms 14 themes. The coverage check finds that concerns about bus access for disabled residents, raised in 23 submissions, are missing. It adds them as a separate theme and reruns the check, which passes. The consultation lead approves the summary draft.

More agents for policy makers

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
Compliance · Government

Public Records Request Handling Agent

A timely, complete response with correct redactions and a record of each decision

10 steps2 checks6 jobs