Automation library · Customer support

Answer onboarding questions in Slack with Anthropic

Started by an event in a connected app, and works across Google Sheets, Pinecone and Slack. It puts Claude and OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 33 steps, 4 branches: large, and worth reading before you trust it with anything live.

LargeCalls a model: Claude, OpenAIRetrieval

Download free
33 stepsLarge: read it before trusting it with anything live
4Branches: places the flow splits
0Loops or waits
3Services it connects to

The flow

Starts it 2Model 8Logic 14Service 9

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

  1. 1When Slack Mention ReceivedSlack triggerStarts it
  2. 2OpenAI Embeddings for QueryEmbeddings Open AiModel
  3. 3Claude Chat ModelLm Chat AnthropicModel
  4. 4Trigger ManuallyManual triggerStarts it
  5. 5OpenAI EmbeddingsEmbeddings Open AiModel
  6. 6Split Text Recursively by CharText Splitter Recursive Character Text SplitterModel
  7. 7Parse Slack Message FieldsCodeLogic
  8. 8Pinecone Knowledge BaseVector Store PineconeModel
  9. 9AI Response AgentAgentModel
  10. 10Fetch Pinecone Index HostHttp RequestService
  11. 11Pinecone Vector StorageVector Store PineconeModel
  12. 12Load Default Document DataDocument Default Data LoaderModel
  13. 13If Message Not EmptyIfLogic
  14. 14Check If Escalation NeededIfLogic
  15. 15Clear Pinecone NamespaceHttp RequestService
  16. 16Read Sender from Roster SheetsGoogle SheetsService
  17. 17Read Escalation Manager SheetsGoogle SheetsService
  18. 18Check If No Match FoundIfLogic
  19. 19Download Policy DocumentHttp RequestService
  20. 20Prepare Company & CEO InfoCodeLogic
  21. 21Prepare Team Roster InfoCodeLogic
  22. 22If Sender Found in RosterIfLogic
  23. 23Construct Escalation MessageCodeLogic
  24. 24Read Fallback Manager from SheetsGoogle SheetsService
  25. 25Construct Answer MessageCodeLogic
  26. 26Extract Policy Document SectionsCodeLogic
  27. 27Merge Source DataMergeLogic
  28. 28Set Identified Sender DetailsSetLogic
  29. 29Notify Sender Not in RosterSlackService
  30. 30Post Reply to SlackSlackService
  31. 31Construct Fallback MessageCodeLogic
  32. 32Fetch Thread Replies from SlackHttp RequestService
  33. 33Prepare Thread Context DataCodeLogic

How it's built

Starts on
An event in a connected app
Steps
33, with 4 branches
Size
Large: read it before trusting it with anything live
Connects to
Google Sheets, Pinecone, Slack
Model
Claude, OpenAI
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 Google Sheets, Pinecone and Slack accounts, and a key for Claude and OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an event in a connected app.

Does it use AI?

Yes. It calls Claude and OpenAI. 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 33 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 33 steps before you point it at anything that matters.