The flow
Starts it 1Model 2Logic 5Service 5
The steps in the order they run, from what starts it.
- 1Google Gemini Chat ModelLm Chat Google GeminiModel
- 2Watch Gmail (New Inbound)Gmail triggerStarts it
- 3Draft Reply (AI Agent)AgentModel
- 4Filter: Allowed SenderFilterLogic
- 5Wait for Response - Approve Auto-ReplySlackService
- 6Find Contact by EmailHubspotService
- 7If Approved?IfLogic
- 8Set Record TypesCodeLogic
- 9Reply to a messageGmailService
- 10List Contact AssociationsHttp RequestService
- 11Build Batch Read RequestsCodeLogic
- 12Batch Read ObjectsHttp RequestService
- 13Normalize CRM Context for LLMCodeLogic
How it's built
- Starts on
- An arriving email
- Steps
- 13, with 1 branch
- Size
- Medium: a working afternoon
- Connects to
- Gmail, HubSpot, Slack
- Model
- Gemini
Questions
What does it need to run?
An n8n account, plus your own Gmail, HubSpot and Slack accounts, and a key for Gemini. You connect your own accounts after importing it; none are included.
What starts it?
It starts on an arriving email.
Does it use AI?
Yes. It calls Gemini. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 13 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.
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 13 steps before you point it at anything that matters.