AI assistant for company policies and benefits

Employees ask in chat about leave, benefits or who to contact — the assistant answers from company documents in your HR system.

  • Answers employee questions around the clock
  • Draws on company documents, doesn't make things up
  • Points to the right person or department
  • Takes routine questions off HR's plate
Default Data LoaderEmbeddings OpenAIBambooHRSupabase Vector StoreChat
Set it upScriptera

How it works

To connect Redis and Default Data Loader, you don't need a developer: a ready-made scenario links them in minutes.

  1. Starts when: When clicking ‘Test workflow’
  2. Then: GET all files
  3. Check: Filter out files from undesired categories
  4. Then: Split out individual files
  5. Check: Filter out non-pdf files
  6. Then: Download file from BambooHR
  7. Then: Supabase Vector Store
  8. Then: Default Data Loader
  9. Then: Embeddings OpenAI
  10. Then: Recursive Character Text Splitter
  11. Then: Window Buffer Memory
  12. Then: OpenAI Chat Model
  13. Then: Vector Store Tool
  14. Then: OpenAI Chat Model1
  15. Then: Embeddings OpenAI1
  16. Then: Employee Lookup Tool
  17. Then: OpenAI Chat Model2
  18. Then: OpenAI Chat Model3
  19. Then: OpenAI Chat Model4
  20. Then: Auto-fixing Output Parser
  21. Then: OpenAI Chat Model5
  22. Then: Structured Output Parser
  23. Starts when: Employee initiates a conversation
  24. Then: HR AI Agent
  25. Then: Supabase Vector Store Retrieval
  26. Starts when: AI-Powered HR Benefits and Company Policies Chatbot
  27. Then: Text Classifier
  28. Then: GET all employees
  29. Check: Filter out other employees
  30. Then: Stringify employee record for response
  31. Then: GET all employees (second path)
  32. Then: Extract departments
  33. Then: Ensure uniqueness in department list
  34. Then: Extract department
  35. Then: Retrieve all employees
  36. Check: Filter out other departments
  37. Then: Extract relevant employee fields
  38. Then: Identify most senior employee
  39. Then: Format name for response

You can launch this Redis + Default Data Loader integration in Scriptera: describe the task in plain words — the scenario is built, launched and monitored for you.

Similar scenarios