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 customer success managers

Churn Risk Review Agent

Find at-risk accounts early with a concrete save plan

Churn Risk Review Agent: what goes in, what the agent does and what you get

What it does

Customer success managers cannot watch every account closely, and churn often shows warning signs weeks early. Each week this agent scores every account on churn risk using usage trends, support tickets, survey scores, payment issues and contact changes, such as a sponsor leaving. Before trusting the scores, it tests them on last quarter: would they have flagged the accounts that churned without flagging many that renewed? If there are too many false alarms, it adjusts the weights and scores again. For high-risk accounts it writes a short reason and a save plan: who to talk to, what value to show and what to fix. The CSM reviews the risk list and approves all outreach. Edge case: an account with low usage but a recent expansion is not flagged high.

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 Weekly risk review 2 USES A TOOL Pull usage, tickets, surveys, billing and contacts 3 DOES Score risk per account 4 CHECKS THE RESULT Would the scoring have flagged last quarter'schurned accounts without many false alarms? If not: adjust signal weights and score again. Back tostep 3. 5 DOES Remove flags explained by recent expansion or knownseasonal dips 6 USES A TOOL Draft reasons and save plans for high-risk accounts 7 CHECKS THE RESULT Does each save plan name a contact, a value pointand a fix? If not: fill the gaps from account notes or ask the CSM.Back to step 6. 8 YOU APPROVE CSM approves outreach 9 RESULT Risk list and plans saved
Read the steps as a list
  1. Weekly risk review
  2. Pull usage, tickets, surveys, billing and contacts
  3. Score risk per account
  4. Would the scoring have flagged last quarter's churned accounts without many false alarms?If not: adjust signal weights and score again. Back to step 3.
  5. Remove flags explained by recent expansion or known seasonal dips
  6. Draft reasons and save plans for high-risk accounts
  7. Does each save plan name a contact, a value point and a fix?If not: fill the gaps from account notes or ask the CSM. Back to step 6.
  8. CSM approves outreachThe agent waits here for your OK.
  9. Risk list and plans saved

How it decides

It weights signals that came before past churn and requires two signals for a high-risk flag.

  • High risk needs two signals
  • Sponsor departure is always a signal
  • Recent expansion lowers risk

Make it yours

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

  • Signals and weights
  • Risk threshold
  • Review day
  • Save plan template

What keeps you in control

It always asks you first

  • Customer outreach
  • Offering discounts

Hard limits

  • Never offers discounts
  • Never contacts customers itself

It stops when

  • Done: weekly list delivered
  • Stop: usage data delayed

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 happensThe first scoring on July 7 flagged 41 of 180 accounts. Tested on last quarter, it caught 7 of 8 churned accounts but also 30 that renewed, so the check failed. The agent raised the weight on sponsor changes, lowered ticket volume and re-scored. It flagged 16 and still caught 7 of 8. The CSM approved outreach to the top 10.

More agents for customer success managers