Automation library · Customer support

Handle WhatsApp support chats with OpenRouter and Pinecone

Started by an incoming WhatsApp message, and works across Pinecone and WhatsApp. It puts Gemini and OpenRouter behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 44 steps, 6 branches: large, and worth reading before you trust it with anything live.

LargeCalls a model: Gemini, OpenRouterRetrieval

Download free
44 stepsLarge: read it before trusting it with anything live
6Branches: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 5Model 7Logic 10Service 22

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

  1. 1WhatsApp TriggerWhats App triggerStarts it
  2. 2OpenRouter Model1Lm Chat Open RouterModel
  3. 3Simple MemoryMemory Buffer WindowModel
  4. 4Create CaseHttp Request ToolService
  5. 5GeminiEmbeddings Google GeminiModel
  6. 6Outbound WebhookWebhookStarts it
  7. 7Summarize WebhookWebhookStarts it
  8. 8OpenRouter ModelLm Chat Open RouterModel
  9. 9Route by EventSwitchLogic
  10. 10AI Agent1AgentModel
  11. 11Knowledge BaseVector Store PineconeModel
  12. 12Has Media?IfLogic
  13. 13Fetch MessagesHttp RequestService
  14. 14SummarizeChain LlmModel
  15. 15Store ReadHttp RequestService
  16. 16Store SentHttp RequestService
  17. 17Store DeliveredHttp RequestService
  18. 18Contact LookupHttp RequestService
  19. 19Prepare Agent ReplySetLogic
  20. 20Route By Media TypeSwitchLogic
  21. 21Send TextWhats AppService
  22. 22Respond SummaryRespond To WebhookStarts it
  23. 23Normalise MessageSetLogic
  24. 24Send messageWhats AppService
  25. 25Send Media - ImageWhats AppService
  26. 26Send Media - VideoWhats AppService
  27. 27Send Media - DocumentWhats AppService
  28. 28Send Media - AudioWhats AppService
  29. 29Log OutboundHttp RequestService
  30. 30Route by Message TypeSwitchLogic
  31. 31Store Outbound MsgHttp RequestService
  32. 32Respond OKRespond To WebhookStarts it
  33. 33Store ReactionHttp RequestService
  34. 34Store Inbound MsgHttp RequestService
  35. 35Get Media URLWhats AppService
  36. 36Case Open CheckHttp RequestService
  37. 37Download MediaHttp RequestService
  38. 38Case Open?IfLogic
  39. 39Upload MediaHttp RequestService
  40. 40Reply RouterIfLogic
  41. 41Prepare Media MessageSetLogic
  42. 42Prepare Static ReplySetLogic
  43. 43Send Static ReplyWhats AppService
  44. 44Store Static OutboundHttp RequestService

How it's built

Starts on
An incoming WhatsApp message
Steps
44, with 6 branches
Size
Large: read it before trusting it with anything live
Connects to
Pinecone, WhatsApp
Model
Gemini, 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 Pinecone and WhatsApp accounts, and a key for Gemini and 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 Gemini and 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?

Take your time. At 44 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 44 steps before you point it at anything that matters.