# Predict customer churn daily with LLM and Slack: n8n workflow

> Started by a clock, and works across Email and Postgres. 16 steps, 1 branch: a working afternoon to understand properly.

Source: https://millionrounds.com/workflow/predict-customer-churn-daily-with-llm-and-slack (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Alerts and monitoring](https://millionrounds.com/workflows?category=Alerts+and+monitoring#library)

# Predict customer churn daily with LLM and Slack

Started by a clock, and works across Email and Postgres. 16 steps, 1 branch: a working afternoon to understand properly.

Medium

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fpredict-customer-churn-daily-with-llm-and-slack)

**16 steps** Medium: a working afternoon

**1** Branch: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 1 Logic 7 Service 8

The steps in the order they run, from what starts it.

- 1 **Daily churn analysis at 2 AM** Schedule trigger *Starts it*
- 2 **Fetch active customer profiles** Http Request *Service*
- 3 **Fetch customer activity logs (30 days)** Http Request *Service*
- 4 **Fetch transaction history (90 days)** Http Request *Service*
- 5 **Merge customer and activity data** Merge *Logic*
- 6 **Engineer behavioral features** Code *Logic*
- 7 **Call ML churn prediction model** Http Request *Service*
- 8 **Score and classify churn risk** Code *Logic*
- 9 **Route by risk level** Switch *Logic*
- 10 **Create retention campaign task** Http Request *Service*
- 11 **Store churn predictions in database** Postgres *Service*
- 12 **Generate churn analytics report** Code *Logic*
- 13 **Filter at-risk customers** Filter *Logic*
- 14 **Post churn alert to Slack** Http Request *Service*
- 15 **Email report to customer success team** Email Send *Service*
- 16 **Log analysis completion** Code *Logic*

## How it's built

- **Starts on:** A clock
- **Steps:** 16, with 1 branch
- **Size:** Medium: a working afternoon
- **Connects to:** Email, Postgres
- **Model:** None. This is plumbing, not judgement

## Questions

What does it need to run?

An n8n account, plus your own Email and Postgres accounts. You connect your own accounts after importing it; none are included.

What starts it?

It starts on a clock.

Does it use AI?

No. Every step is fixed logic or a call to a service, so it does the same thing every time.

How long does it take to set up?

Plan an afternoon. 16 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 16 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fpredict-customer-churn-daily-with-llm-and-slack)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Email](https://millionrounds.com/workflows?service=Email#library)[Postgres](https://millionrounds.com/workflows?service=Postgres#library)

## Workflows like it

Also alerts and monitoring, with the same services where possible, closest in size first.

- [**Company Review Monitor with SendGrid and HubSpot** 16 steps · Email, HubSpot](https://millionrounds.com/workflow/company-review-monitor-with-sendgrid-and-hubspot)
- [**Detect and route cybersecurity threats with SIEM and Slack** 16 steps · Email, Postgres](https://millionrounds.com/workflow/detect-and-route-cybersecurity-threats-with-siem-and-slack)
- [**Monitor Klaviyo list decay with Postgres and Gmail** 16 steps · Gmail, Postgres](https://millionrounds.com/workflow/monitor-klaviyo-list-decay-with-postgres-and-gmail)
- [**Monitor cybersecurity compliance and send weekly reports** 16 steps · Email, Postgres](https://millionrounds.com/workflow/monitor-cybersecurity-compliance-and-send-weekly-reports)
- [**Automate website monitoring with OpenAI and MCP** 16 steps · calls a model · Email, Google Sheets](https://millionrounds.com/workflow/automate-website-monitoring-with-openai-and-mcp)
- [**Aggregate error alerts and send consolidated reports** 17 steps · Email, Jira](https://millionrounds.com/workflow/aggregate-error-alerts-and-send-consolidated-reports)