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 analysts

Program Evaluation Monitoring Agent

A quarterly program status note based on checked indicator data

MonitoringReportingAnalysisGovernment
See how it worksGet access
Program Evaluation Monitoring Agent: what goes in, what the agent does and what you get

What it does

Public programs report outputs and outcomes every quarter, but data arrives from different agencies in different formats and with gaps. This agent collects the latest indicator data and first checks quality: missing months or jumps with no explanation trigger a correction request to the data owner, and it waits for the resubmission before going further. It then compares each indicator with its pro-rated target and the logic model. Anything more than 10% below target counts as off track. For those, it looks in program records for reasons, never guessing. It drafts a short status note with charts. The analyst reviews it and decides what goes to officials. Edge case: if an indicator definition changed mid-year, the agent shows the old and new series separately instead of joining them into one line.

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 Quarterly data due date 2 USES A TOOL Collect indicator data from agency submissions 3 CHECKS THE RESULT Is data complete and free of unexplained jumps? If not: send a correction request to the data owner andwait for resubmission. Back to step 2. 4 DOES Compare each indicator with its pro-rated target 5 DOES Look for reasons in program records for off-trackindicators 6 USES A TOOL Draft the status note with charts 7 YOU APPROVE Analyst approves the note for officials 8 RESULT Quarterly status note filed
Read the steps as a list
  1. Quarterly data due date
  2. Collect indicator data from agency submissions
  3. Is data complete and free of unexplained jumps?If not: send a correction request to the data owner and wait for resubmission. Back to step 2.
  4. Compare each indicator with its pro-rated target
  5. Look for reasons in program records for off-track indicators
  6. Draft the status note with charts
  7. Analyst approves the note for officialsThe agent waits here for your OK.
  8. Quarterly status note filed

How it decides

An indicator is off track when it is more than 10% below its pro-rated target. Data with missing months or sudden jumps is checked with the source before use.

  • More than 10% below target is off track
  • Changed definitions are shown as separate series
  • Reasons must come from program records, not guesses

Make it yours

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

  • Off-track threshold (default 10% below target)
  • Reporting frequency
  • Indicators to include
  • Note format and audience

What keeps you in control

It always asks you first

  • Analyst approves before any note reaches officials

Hard limits

  • Never publishes findings
  • Does not contact program participants

It stops when

  • Done: all indicators assessed
  • Stop: data owner has not resubmitted after two requests; report the gap

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 Q2, a job training program reported 1,840 enrollments, but one county showed zero for May. The completeness check failed, and the agent sent a correction request. The county resubmitted 112 enrollments, and the check passed. Completions were 22% below the pro-rated target. Program records showed a provider closed in April, which the note cited as a likely cause. The analyst approved the note for the July briefing.

More agents for policy analysts

Reporting · Research

Stakeholder Brief Update Agent

Current, documented stakeholder briefs.

8 steps1 check5 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
Creating · Automation

Amendment Comparison and Impact Agent

A short briefing note on what each amendment changes, with conflicts and knock-on effects listed and sourced

11 steps2 checks3 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