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

Budget Scenario Optimization Agent

A small set of balanced, rule-compliant budget scenarios ranked by how well they meet priorities

Budgets and moneyDecisionsGovernmentFinanceManagement
See how it worksGet access
Budget Scenario Optimization Agent: what goes in, what the agent does and what you get

What it does

A budget request lists many wants, while revenue, mandates and legal limits cap what can be done. This agent builds budget scenarios from the stated priorities and the legal minimums, such as required reserves and mandated services. It tests each scenario against projected revenue, mandates and rules, then ranks them by how much of the priority list they fund. If a scenario fails a test, for example it breaks the reserve rule or spends more than revenue, it adjusts the lowest priority items and reruns. It checks that the final scenarios balance and that every mandate is fully funded. It reports what each scenario funds, cuts and risks. The official chooses. Edge case: a grant that requires a local match is funded only when the match is in the same scenario.

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, continueYes, continueApprovedNoNo 1 STARTS WHEN Budget cycle opens or revenue estimate changes 2 USES A TOOL Load requests, revenue forecast, mandates andreserve rules 3 DOES Fund mandates and legal minimums first 4 DOES Build scenarios by funding priorities in rank order 5 CHECKS THE RESULT Does each scenario balance and meet the reserverule? If not: reduce the lowest-priority items in thatscenario and rerun. Back to step 4. 6 CHECKS THE RESULT Are matching grants funded together with theirmatch? If not: fund the match or remove the grant from thescenario. Back to step 4. 7 DOES Test each scenario against a lower revenue case 8 DOES Rank scenarios by share of priorities funded 9 YOU APPROVE Official chooses a scenario or asks for changes 10 RESULT Scenario comparison and chosen budget
Read the steps as a list
  1. Budget cycle opens or revenue estimate changes
  2. Load requests, revenue forecast, mandates and reserve rules
  3. Fund mandates and legal minimums first
  4. Build scenarios by funding priorities in rank order
  5. Does each scenario balance and meet the reserve rule?If not: reduce the lowest-priority items in that scenario and rerun. Back to step 4.
  6. Are matching grants funded together with their match?If not: fund the match or remove the grant from the scenario. Back to step 4.
  7. Test each scenario against a lower revenue case
  8. Rank scenarios by share of priorities funded
  9. Official chooses a scenario or asks for changesThe agent waits here for your OK.
  10. Scenario comparison and chosen budget

How it decides

Mandates and legal minimums are funded first. Remaining money goes to priorities in rank order, subject to match requirements and the reserve rule.

  • Fund mandates and legal minimums before any priority
  • Reject a scenario that leaves reserves below the policy level
  • Test with revenue 3% below forecast
  • Fund a grant only with its required match

Make it yours

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

  • Priority ranking
  • Reserve requirement (default 8%)
  • Downside revenue case (default minus 3%)
  • Number of scenarios to build

What keeps you in control

It always asks you first

  • Choice of the final scenario

Hard limits

  • Never changes the official budget system
  • Does not set priorities itself

It stops when

  • Done: the official selects a scenario
  • Stop: revenue forecast is missing

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 happensRequests were $214 million against $198 million of revenue. The first scenario funded 11 of 14 priorities but left reserves at 6% against a 8% rule, so the check failed. The agent cut a $4 million road item and a $2 million training line and reran it, reaching 8.1%. A scenario at revenue minus 3% lost one more priority. The official chose scenario B.

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