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 program managers

Cross-Agency Implementation Tracker Agent

A current picture of implementation by agency, with delays, blockers and follow-ups on record

Cross-Agency Implementation Tracker Agent: what goes in, what the agent does and what you get

What it does

A policy that needs five agencies to act usually stalls at one of them, and the team learns about it months later. This agent lists the implementation steps by agency with owners, dates and dependencies. Each week it collects status updates from the agencies by email or form and updates the plan. It flags delays and traces what each delay blocks downstream. For late items, it drafts a follow-up message to the right contact. When replies come in, it checks whether the answer gives a date and a reason, and asks again if not. It rechecks the critical path after each update. The lead approves all messages. Edge case: an agency that reports a step done with no evidence is marked unverified until a document arrives.

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, continueApprovedYes, continueNoNo 1 STARTS WHEN Weekly status cycle 2 USES A TOOL Request and collect status updates from each agency 3 DOES Update each step's status in the plan 4 CHECKS THE RESULT Does each step marked complete have evidence? If not: mark it unverified and request the evidence.Back to step 3. 5 DOES Flag late steps and trace what they block 6 DOES Recalculate the critical path 7 DOES Draft follow-up messages for late or unclear items 8 YOU APPROVE Lead approves messages before they are sent 9 USES A TOOL Send and log replies 10 CHECKS THE RESULT Does each reply give a reason and a new date? If not: draft a second request for the missinginformation. Back to step 7. 11 RESULT Weekly implementation report
Read the steps as a list
  1. Weekly status cycle
  2. Request and collect status updates from each agency
  3. Update each step's status in the plan
  4. Does each step marked complete have evidence?If not: mark it unverified and request the evidence. Back to step 3.
  5. Flag late steps and trace what they block
  6. Recalculate the critical path
  7. Draft follow-up messages for late or unclear items
  8. Lead approves messages before they are sentThe agent waits here for your OK.
  9. Send and log replies
  10. Does each reply give a reason and a new date?If not: draft a second request for the missing information. Back to step 7.
  11. Weekly implementation report

How it decides

A step is late when its date has passed without confirmed completion. A delay is critical when it blocks a step on the critical path.

  • Mark a step late the day after its due date
  • Treat a step as unverified without a document or confirmation
  • Escalate to the lead when a critical-path item is 7 days late
  • Ask for a date and a reason in every reply

Make it yours

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

  • Reporting day
  • Late and escalation rules
  • Evidence required for completion
  • Contact list per agency

What keeps you in control

It always asks you first

  • Follow-up messages to agencies

Hard limits

  • Never contacts an agency without lead approval
  • Does not change dates in the plan without a reply

It stops when

  • Done: the weekly report is issued
  • Stop: the plan has no owners or dates

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 housing policy had 26 steps across 5 agencies. The agent found 4 late, one from the health department blocking two others on the critical path. A reply from public works said 'in progress' with no date, so the check failed and it asked again. It then learned that a permit review was waiting for staff. The lead approved 4 messages and escalated the health item.

More agents for program managers