# Build a WhatsApp customer support bot with OpenAI and CRM: n8n workflow

> Started by another system calling it. It calls services over plain HTTP rather than through connectors.

Source: https://millionrounds.com/workflow/build-a-whatsapp-customer-support-bot-with-openai-and-crm (Millionrounds; every figure on the page links to its filing or article)

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

# Build a WhatsApp customer support bot with OpenAI and CRM

Started by another system calling it. It calls services over plain HTTP rather than through connectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 22 steps, 1 branch: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-a-whatsapp-customer-support-bot-with-openai-and-crm)

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

**1** Branch: places the flow splits

**0** Loops or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 1 Model 8 Logic 5 Service 8

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

- 1 **OpenAI Chat Model1** Lm Chat Open Ai *Model*
- 2 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 3 **OpenAI Chat Model2** Lm Chat Open Ai *Model*
- 4 **crm_search_tool** Http Request Tool *Service*
- 5 **save_crm_record_tool** Http Request Tool *Service*
- 6 **get_loyalty_points_tool** Http Request Tool *Service*
- 7 **items_search_tool** Http Request Tool *Service*
- 8 **branches_search_tool** Http Request Tool *Service*
- 9 **categories_search_tool** Http Request Tool *Service*
- 10 **Webhook: Receive WhatsApp message** Webhook *Starts it*
- 11 **Simple Memory-2** Memory Buffer Window *Model*
- 12 **Simple Memory** Memory Buffer Window *Model*
- 13 **AI Agent** Agent *Model*
- 14 **AI Agent Router: Classify msg** Agent *Model*
- 15 **Structured Output Parser** Output Parser Structured *Model*
- 16 **Send Answer to User's WhatsApp** Evolution Api *Service*
- 17 **Switch** Switch *Logic*
- 18 **Branches System Prompt** Set *Logic*
- 19 **Menu System Prompt** Set *Logic*
- 20 **Orders System Prompt** Set *Logic*
- 21 **Complaints System Prompt** Set *Logic*
- 22 **Send WhatsApp Greeting** Evolution Api *Service*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 22, with 1 branch
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, 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. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 22 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 22 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%2Fbuild-a-whatsapp-customer-support-bot-with-openai-and-crm)
- **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.

## Workflows like it

Also customer support, with the same services where possible, closest in size first.

- [**AI WhatsApp support with Gemini and Twilio** 22 steps · calls a model · Airtable, Google Drive](https://millionrounds.com/workflow/ai-whatsapp-support-with-gemini-and-twilio)
- [**AI-powered ticket triage with OpenAI and Postgres** 22 steps · calls a model · Postgres, Slack](https://millionrounds.com/workflow/ai-powered-ticket-triage-with-openai-and-postgres)
- [**Assess GitHub bus-factor risk in GitHub with Claude and Slack** 22 steps · calls a model · Slack](https://millionrounds.com/workflow/assess-github-bus-factor-risk-in-github-with-claude-and-slac)
- [**Automate support ticket triage and resolution with Jira** 22 steps · calls a model · Jira](https://millionrounds.com/workflow/automate-support-ticket-triage-and-resolution-with-jira)
- [**Build a website RAG support chatbot with Firecrawl** 22 steps · calls a model · Pinecone](https://millionrounds.com/workflow/build-a-website-rag-support-chatbot-with-firecrawl)
- [**Build a website-powered customer support chatbot with Decodo** 22 steps · calls a model · Pinecone](https://millionrounds.com/workflow/build-a-website-powered-customer-support-chatbot-with-decodo)