The flow
Starts it 3Model 2Logic 7Service 4
The steps in the order they run, from what starts it.
- 1Webhook - New Support MessageWebhookStarts it
- 2Poll Support InboxSchedule triggerStarts it
- 3Webhook - Human Approval ResponseWebhookStarts it
- 4OpenAI Chat ModelLm Chat Open AiModel
- 5Normalize Message ContextSetLogic
- 6Filter - Approved by Human?FilterLogic
- 7AI - Classify and Draft ReplyAgentModel
- 8Python - Classify Sensitivity TierCodeLogic
- 9Send Reply to CustomerHttp RequestService
- 10JS - Parse AI ClassificationCodeLogic
- 11Send Slack Reply (if Slack channel)Http RequestService
- 12Route - Sensitive or Routine?FilterLogic
- 13Wait For ResultWaitLogic
- 14Notify Human via SlackHttp RequestService
- 15Log to Support Audit SheetHttp RequestService
- 16Wait - Human Review WindowWaitLogic
How it's built
- Starts on
- Another system calling it
- Steps
- 16, 2 loops or waits
- Size
- Medium: a working afternoon
- Connects to
- Nothing by connector; it calls services over plain HTTP
- Model
- OpenAI
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. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 16 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 itNothing 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 16 steps before you point it at anything that matters.