Automation library · Customer support

Automate customer support with Mintlify and Zendesk AI

Started by another system calling it. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to OpenRouter. 32 steps, 5 branches: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenRouter

32 stepsLarge: read it before trusting it with anything live
5Branches: places the flow splits
0Loops or waits
0Services by connector: it calls them over plain HTTP

The flow

Starts it 1Model 6Logic 15Service 10

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

  1. 1OpenRouter Chat ModelLm Chat Open RouterModel
  2. 2WebhookWebhookStarts it
  3. 3OpenRouter Chat Model1Lm Chat Open RouterModel
  4. 4OpenRouter Chat Model2Lm Chat Open RouterModel
  5. 5AI AgentAgentModel
  6. 6Fetch Zendesk ticketHttp RequestService
  7. 7Check uncertaintyAgentModel
  8. 8Message classifierAgentModel
  9. 9Parse AI responseCodeLogic
  10. 10Check if human agent is assignedSwitchLogic
  11. 11Uncertainty routerSwitchLogic
  12. 12Message routerSwitchLogic
  13. 13If human assigned, don't replyNo OpLogic
  14. 14Fetch ticket conversationHttp RequestService
  15. 15If uncertain, don't replyNo OpLogic
  16. 16Reply ticket and put on pendingHttp RequestService
  17. 17Billing suspected - escalateHttp RequestService
  18. 18Delete ticketHttp RequestService
  19. 19Fraud suspected - escalateHttp RequestService
  20. 20Look for Mintlify topicIdCodeLogic
  21. 21Parse conversationCodeLogic
  22. 22New ticket?SwitchLogic
  23. 23Count AI repliesCodeLogic
  24. 24Create Mintlify Chat TopicHttp RequestService
  25. 25Mintlify generated response (existing)Http RequestService
  26. 26Check how many times the AI repliedSwitchLogic
  27. 27Add Mintlify topicId to ticket tagsHttp RequestService
  28. 28Parse mintlify responseCodeLogic
  29. 29Flip conversation to get the last messageCodeLogic
  30. 30If more that x replies, don't replyNo OpLogic
  31. 31Add Mintlify topicID to ticketCodeLogic
  32. 32Mintlify generated response (new)Http RequestService

How it's built

Starts on
Another system calling it
Steps
32, with 5 branches
Size
Large: read it before trusting it with anything live
Connects to
Nothing by connector; it calls services over plain HTTP
Model
OpenRouter

Questions

What does it need to run?

An n8n account, and a key for OpenRouter. 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 OpenRouter. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 32 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 32 steps before you point it at anything that matters.