Automation library · Customer support

Answer HR policy and benefits questions with BambooHR

Started by someone opening a chat with it, and works across Supabase vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 39 steps: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

Download free
39 stepsLarge: read it before trusting it with anything live
0Branches: places the flow splits
0Loops or waits
1Service it connects to

The flow

Starts it 3Model 21Logic 10Service 5

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

  1. 1When clicking ‘Test workflow’Manual triggerStarts it
  2. 2Embeddings OpenAIEmbeddings Open AiModel
  3. 3Recursive Character Text SplitterText Splitter Recursive Character Text SplitterModel
  4. 4Window Buffer MemoryMemory Buffer WindowModel
  5. 5OpenAI Chat ModelLm Chat Open AiModel
  6. 6OpenAI Chat Model1Lm Chat Open AiModel
  7. 7Embeddings OpenAI1Embeddings Open AiModel
  8. 8Employee Lookup ToolTool WorkflowModel
  9. 9OpenAI Chat Model2Lm Chat Open AiModel
  10. 10OpenAI Chat Model3Lm Chat Open AiModel
  11. 11OpenAI Chat Model4Lm Chat Open AiModel
  12. 12OpenAI Chat Model5Lm Chat Open AiModel
  13. 13Structured Output ParserOutput Parser StructuredModel
  14. 14Employee initiates a conversationChat triggerStarts it
  15. 15AI-Powered HR Benefits and Company Policies ChatbotExecute Workflow triggerStarts it
  16. 16GET all filesBamboo HrService
  17. 17Supabase Vector StoreVector Store SupabaseModel
  18. 18Default Data LoaderDocument Default Data LoaderModel
  19. 19HR AI AgentAgentModel
  20. 20Vector Store ToolTool Vector StoreModel
  21. 21Supabase Vector Store RetrievalVector Store SupabaseModel
  22. 22Text ClassifierText ClassifierModel
  23. 23Extract departmentInformation ExtractorModel
  24. 24Identify most senior employeeChain LlmModel
  25. 25Auto-fixing Output ParserOutput Parser AutofixingModel
  26. 26Filter out files from undesired categoriesFilterLogic
  27. 27GET all employeesBamboo HrService
  28. 28GET all employees (second path)Bamboo HrService
  29. 29Retrieve all employeesBamboo HrService
  30. 30Format name for responseSetLogic
  31. 31Split out individual filesSplit OutLogic
  32. 32Filter out other employeesFilterLogic
  33. 33Extract departmentsAggregateLogic
  34. 34Filter out other departmentsFilterLogic
  35. 35Filter out non-pdf filesFilterLogic
  36. 36Stringify employee record for responseSetLogic
  37. 37Ensure uniqueness in department listSetLogic
  38. 38Extract relevant employee fieldsAggregateLogic
  39. 39Download file from BambooHRBamboo HrService

How it's built

Starts on
Someone opening a chat with it
Steps
39
Size
Large: read it before trusting it with anything live
Connects to
Supabase vectors
Model
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 Supabase vectors account, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls 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 39 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 39 steps before you point it at anything that matters.