Automation library · AI assistants

Route Chatwoot customer chats to AI and live agents with Groq

Started by another system calling it, and works across Gmail and Pinecone. It puts Gemini and Groq behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 17 steps, 2 branches: a working afternoon to understand properly.

MediumCalls a model: Gemini, GroqRetrieval

Download free
17 stepsMedium: a working afternoon
2Branches: places the flow splits
0Loops or waits
2Services it connects to

The flow

Starts it 1Model 7Logic 6Service 3

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

  1. 1Store Chat Memory in PostgresMemory Postgres ChatModel
  2. 2Send Internal Team EmailGmail ToolService
  3. 3Escalate Chat via HTTPHttp Request ToolService
  4. 4Incoming Chat WebhookWebhookStarts it
  5. 5Use Groq Chat ModelLm Chat GroqModel
  6. 6Generate Google Gemini EmbeddingsEmbeddings Google GeminiModel
  7. 7Implement Google Gemini Chat ModelLm Chat Google GeminiModel
  8. 8AI Customer Support AgentAgentModel
  9. 9Prepare Field EditsSetLogic
  10. 10Utilize Pinecone Vector StoreVector Store PineconeModel
  11. 11Access Knowledge BaseTool Vector StoreModel
  12. 12Split AI MessagesCodeLogic
  13. 13Route by Chat Message TypeSwitchLogic
  14. 14Check Live Agent AssignmentIfLogic
  15. 15Skip OperationNo OpLogic
  16. 16Fetch Live Agent DataHttp RequestService
  17. 17Generate Assignee Agent IDCodeLogic

How it's built

Starts on
Another system calling it
Steps
17, with 2 branches
Size
Medium: a working afternoon
Connects to
Gmail, Pinecone
Model
Gemini, Groq
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 and Pinecone accounts, and a key for Gemini and Groq. 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 Gemini and Groq. 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. 17 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 17 steps before you point it at anything that matters.