# Save at-risk churn customers with OpenAI DeepSeek and Airtable: n8n workflow

> Started by another system calling it, and works across Airtable, Gmail and Telegram. It hands the judgement calls to OpenAI.

Source: https://millionrounds.com/workflow/save-at-risk-churn-customers-with-openai-deepseek-and-airtab (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Chat assistants](https://millionrounds.com/workflows?category=Chat+assistants#library)

# Save at-risk churn customers with OpenAI DeepSeek and Airtable

Started by another system calling it, and works across Airtable, Gmail and Telegram. It hands the judgement calls to OpenAI. 23 steps, 2 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fsave-at-risk-churn-customers-with-openai-deepseek-and-airtab)

**23 steps** Large: read it before trusting it with anything live

**2** Branches: places the flow splits

**0** Loops or waits

**3** Services it connects to

## The flow

Starts it 2 Model 4 Logic 6 Service 11

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

- 1 **Churn Request Received** Webhook *Starts it*
- 2 **OpenAI DeepSeek Model** Lm Chat Open Ai *Model*
- 3 **Lookup Customer in Airtable** Airtable Tool *Service*
- 4 **Monthly Churn Report Trigger** Schedule trigger *Starts it*
- 5 **OpenAI DeepSeek Report Model** Lm Chat Open Ai *Model*
- 6 **Normalize Churn Fields** Set *Logic*
- 7 **AI Retention Strategist** Agent *Model*
- 8 **Fetch Churn Cases from Airtable** Airtable *Service*
- 9 **AI Write Monthly Report** Agent *Model*
- 10 **Validate Churn Input** If *Logic*
- 11 **Extract AI Decision** Set *Logic*
- 12 **Flatten Case Fields** Set *Logic*
- 13 **Format Monthly Report** Set *Logic*
- 14 **Alert Invalid Request on Telegram** Telegram *Service*
- 15 **Log Churn Case in Airtable** Airtable *Service*
- 16 **Compile Churn Stats** Summarize *Service*
- 17 **Email Report to CS Lead** Gmail *Service*
- 18 **Email Invalid Request Notice** Gmail *Service*
- 19 **High Value Customer?** If *Logic*
- 20 **Post Report on Telegram** Telegram *Service*
- 21 **Alert CS Team on Telegram** Telegram *Service*
- 22 **Send Standard Save Email** Gmail *Service*
- 23 **Send Save Offer Email** Gmail *Service*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 23, with 2 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Airtable, Gmail, Telegram
- **Model:** OpenAI

## Questions

What does it need to run?

An n8n account, plus your own Airtable, Gmail and Telegram accounts, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls OpenAI. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 23 steps it is large: read it before trusting it with anything live.

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 23 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%2Fsave-at-risk-churn-customers-with-openai-deepseek-and-airtab)
- **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.

[Airtable](https://millionrounds.com/workflows?service=Airtable#library)[Gmail](https://millionrounds.com/workflows?service=Gmail#library)[Telegram](https://millionrounds.com/workflows?service=Telegram#library)

## Workflows like it

Also chat assistants, with the same services where possible, closest in size first.

- [**Access control for AI agents (RBAC) with Airtable and Telegram** 23 steps · calls a model · Airtable, Telegram](https://millionrounds.com/workflow/access-control-for-ai-agents-rbac-with-airtable-and-telegram)
- [**Assess procurement inflation risk with Groq and Google Sheets** 23 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/assess-procurement-inflation-risk-with-groq-and-google-sheet)
- [**Build a chatbot with RAG** 23 steps · calls a model · Google Docs, Telegram](https://millionrounds.com/workflow/build-a-chatbot-with-rag)
- [**Conversational AI Chatbot with Gemini and Image** 23 steps · calls a model · Telegram](https://millionrounds.com/workflow/conversational-ai-chatbot-with-gemini-and-image)
- [**Create AI Instagram Reels with OpenAI and Veo3** 23 steps · calls a model · Google Sheets, Slack](https://millionrounds.com/workflow/create-ai-instagram-reels-with-openai-and-veo3)
- [**End of turn detection for smoother AI agent chats** 23 steps · calls a model · Redis, Telegram](https://millionrounds.com/workflow/end-of-turn-detection-for-smoother-ai-agent-chats)
