# Turn Amplitude's churn-risk cohort into a weekly CS action list

> Every Monday, an AI customer success analyst pulls your Amplitude churn-risk cohort, tags each user in Intercom by risk tier, and posts a ranked Slack digest to the CS team.

- Workflow type: agent
- Services: Amplitude, Intercom, Slack Bot
- Categories: Customer Support, Product
- Published: 2026-07-17

## What it does

- Pulls your 'Churn Risk' behavioral cohort from Amplitude every Monday morning
- Sorts each at-risk user into a risk tier — drop-in-usage, feature-abandonment, or support-frustration — and tags them in Intercom so downstream save campaigns pick them up
- Drafts a two-sentence 'why they might be leaving' note per account, grounded in the user's actual product behavior
- Posts a ranked Slack digest of the top 20 at-risk accounts with tier, hypothesis, and a one-click link to each Intercom contact
- If the cohort is empty this week, posts a one-line 'no at-risk accounts today' so the team knows the check still ran

## What you'll need

- An Amplitude account with a saved behavioral cohort for at-risk users (default name: 'Churn Risk')
- An Intercom workspace where your Amplitude user IDs line up with Intercom contact IDs
- A Slack workspace and the channel where your CS team should get the weekly digest

## Prompt

Every Monday at 9am, turn our Amplitude churn-risk cohort into a ranked customer success action list. The cohort name should be a user-configurable input on the prompt page (default: "Churn Risk") so teams can point it at whatever behavioral cohort they already maintain in Amplitude.

Step 1 — Find the cohort. Use Amplitude's List Cohorts to locate the behavioral cohort matching the configured name (case-insensitive substring match so "Churn Risk", "churn-risk", or "Churn Risk – Enterprise" all resolve). If nothing matches, post a one-line Slack notice explaining that the cohort could not be found and stop.

Step 2 — Export the cohort. Amplitude's cohort export is asynchronous, so use Request Cohort Download to start the export, then poll Check Cohort Download Status until the job reports JOB COMPLETED (wait a few seconds between polls, and give up after roughly 5 minutes with a Slack error notice if the job never completes). Once complete, call Download Cohort File to pull the CSV of at-risk user IDs and their user properties. If the cohort is empty this week, post a one-line "no at-risk accounts today" message to the CS Slack channel so the team knows the check ran, then stop.

Step 3 — Classify each at-risk user. For every row in the CSV, an AI customer success analyst reads the user's Amplitude properties (last-active date, session counts, feature usage, support signals, plan tier) and assigns exactly one risk tier: drop-in-usage (login/session frequency has dropped sharply), feature-abandonment (adopted a core feature but stopped using it), or support-frustration (recent support tickets, negative signals, error rates). Also draft a two-sentence "why they might be leaving" note per account, grounded in the specific properties you saw, not generic filler.

Step 4 — Tag each user in Intercom. Match each Amplitude user ID to the corresponding Intercom contact (assume they share the same external ID; if a contact can't be resolved, skip it and note it in the digest tail). Then use Intercom's Tag a Contact operation to apply the tag matching the risk tier — "churn-risk-drop-in-usage", "churn-risk-feature-abandonment", or "churn-risk-support-frustration" — so downstream Intercom campaigns and audiences pick them up automatically.

Step 5 — Post the Slack digest. Use Slack Bot's Send a Message to post a ranked digest to the configured CS channel. Include the total count of at-risk users, a short overall summary, and then the top 20 accounts ranked by severity. For each of the top 20 show: account/user identifier, risk tier, the two-sentence hypothesis, and a direct link to the Intercom contact page (https://app.intercom.com/a/apps/{workspace}/users/{intercomContactId}). Keep the message scannable with Slack markdown headers and bullets. If any Intercom lookups failed, list them at the bottom under "Could not resolve in Intercom" so the CS team can fix the mapping.

Inputs the user should be able to configure on the prompt page: the Amplitude cohort name (default "Churn Risk"), the Slack channel to post to, the Intercom workspace slug used in contact URLs, and the maximum number of accounts shown in the ranked list (default 20).

## How to customize

- Change the day and time the digest posts — swap Monday 9am for whatever fits your CS cadence
- Point the workflow at a different Amplitude cohort by editing the cohort name input
- Rename the risk tiers or add new ones (for example, split 'drop-in-usage' into 'weekly-active-drop' and 'monthly-active-drop')
- Adjust the maximum number of accounts included in the ranked list, or route the digest to a specific CS lead's DM instead of a channel

## FAQ

### What if we don't have a cohort called 'Churn Risk' yet?

You can point the workflow at any Amplitude behavioral cohort by name. Set the cohort input to whatever your team already uses (something like 'At-Risk Accounts' or 'Low Engagement 30d' works fine) and the matching is case-insensitive.

### How does it match Amplitude users to Intercom contacts?

It uses the user IDs Amplitude exports in the cohort file to look up Intercom contacts by external ID. If your Amplitude and Intercom teams use different identifiers, any users it can't resolve get listed at the bottom of the Slack digest so you can fix the mapping.

### What happens if there are no at-risk users this week?

You still get a one-line Slack message saying 'no at-risk accounts today' so the team knows the check ran. No Intercom tags get applied and no follow-up work is queued.

### Do the Intercom tags trigger anything on their own?

The tags themselves are just labels, but Intercom lets you build audiences, in-app messages, and email campaigns keyed to any tag. So any save-play sequence you set up against 'churn-risk-drop-in-usage' or the other tiers will pick these users up automatically the moment they're tagged.

### Can we send the digest somewhere other than Slack?

Yes. Swap the Slack step for email, Microsoft Teams, or any other messaging tool the platform supports. The cohort pull, risk tiering, and Intercom tagging stay the same — only the delivery step changes.

Use this prompt in General Input: https://www.generalinput.com/prompts/turn-amplitudes-churn-risk-cohort-into-a-weekly-cs-action-list