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 community managers

Community Health Metrics Agent

Explain monthly community health and its causes

Community Health Metrics Agent: what goes in, what the agent does and what you get

What it does

Leaders ask how the community is doing, and a list of numbers does not answer that. When the month ends, this agent pulls active members, new posts, response times, retention and top contributors. It compares each metric with past months and finds changes above the set threshold, such as 15 percent. For each big change, it looks for a cause, such as an event, a product launch or a gap in moderator coverage. It checks that every big change has an explanation; if one does not, it digs further into the data or asks the community manager. It then drafts a report with the main changes and their causes. Top contributors are only named with their consent. The community manager approves the report before it is shared. Edge case: data from a platform outage is marked so it does not distort the trend lines.

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 Month ends 2 USES A TOOL Pull community metrics 3 DOES Compare with past months 4 CHECKS THE RESULT Is every big change explained? If not: search events and releases for causes. Back tostep 3. 5 USES A TOOL Draft the report 6 YOU APPROVE Community manager approves 7 RESULT Report shared
Read the steps as a list
  1. Month ends
  2. Pull community metrics
  3. Compare with past months
  4. Is every big change explained?If not: search events and releases for causes. Back to step 3.
  5. Draft the report
  6. Community manager approvesThe agent waits here for your OK.
  7. Report shared

How it decides

Changes above 15% get a cause search.

  • Changes above 15% need a cause
  • Outage periods marked
  • Top contributors listed with consent

Make it yours

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

  • Change threshold
  • Metrics
  • Report format

What keeps you in control

It always asks you first

  • Report

Hard limits

  • Never shares individual activity without consent
  • Labels causes as likely

It stops when

  • Done: report shared
  • Stop: analytics unavailable

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 August the agent pulls active members, posts, replies and response time. Active members fell 18% from July. The check fails: the change has no explanation yet. The agent compares with past years and finds a similar August dip, plus a 2-day outage on August 14. It adds both notes. The community manager approves the report, and it is shared with leadership.

More agents for community managers