Automation library · Customer support

Run a multilingual WhatsApp support assistant with OpenAI

Started by an incoming WhatsApp message, and works across Gmail, Google Sheets and WhatsApp. It puts OpenRouter behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 18 steps, 2 branches: a working afternoon to understand properly.

MediumCalls a model: OpenRouterRetrieval

18 stepsMedium: a working afternoon
2Branches: places the flow splits
0Loops or waits
3Services it connects to

The flow

Starts it 2Model 4Logic 6Service 6

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

  1. 1WhatsApp TriggerWhats App triggerStarts it
  2. 2OpenRouter Chat ModelLm Chat Open RouterModel
  3. 3Conversation MemoryMemory Buffer WindowModel
  4. 4Notify Human InputExecute Workflow triggerStarts it
  5. 5Notify HumanTool WorkflowModel
  6. 6Business ConfigSetLogic
  7. 7AI Agent - AssistantAgentModel
  8. 8Gmail - Notify HumanGmailService
  9. 9Classify MessageCodeLogic
  10. 10WhatsApp - Reply CustomerWhats AppService
  11. 11Is Image?IfLogic
  12. 12Prepare Conversation LogCodeLogic
  13. 13Prepare Email NotificationCodeLogic
  14. 14Requests Human?IfLogic
  15. 15Google Sheets - Log ConversationGoogle SheetsService
  16. 16Gmail - Send NotificationGmailService
  17. 17WhatsApp - Reply NotificationWhats AppService
  18. 18Google Sheets - Log Image/HumanGoogle SheetsService

How it's built

Starts on
An incoming WhatsApp message
Steps
18, with 2 branches
Size
Medium: a working afternoon
Connects to
Gmail, Google Sheets, WhatsApp
Model
OpenRouter
Retrieval
Answers are drawn from documents you supply, not from the model alone

Questions

What does it need to run?

An n8n account, plus your own Gmail, Google Sheets and WhatsApp accounts, and a key for OpenRouter. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an incoming WhatsApp message.

Does it use AI?

Yes. It calls OpenRouter. 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?

Plan an afternoon. 18 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 18 steps before you point it at anything that matters.