Skip to content
NEWMarketplace and the trig8n Agent: sell what you build, and get plans and changes that are tested before you see them. See what is new

Library / RAG & Knowledge Bases

RAG & Knowledge Bases

Answer HR Policy Questions from BambooHR with OpenAI

When a chat message arrives, an OpenAI agent searches policy documents stored in Supabase and BambooHR employee data to answer HR questions.

What it does

### AI Chatbot Operating Guidelines - When an employee asks for a contact person, first attempt to find the relevant contact in company_files. - If a contact person is found but their details (e.g., email or phone number) are missing, use the employee_lookup_tool to retrieve their contact details. - If no contact person is found: 1. Use the employee_lookup_tool with "HR" (or another relevant department) to retrieve the most senior person in that department. 2. If no senior contact is found, ask the employee for their name. 3. Use the employee_lookup_tool to retrieve their supervisor’s name. 4. Use the employee_lookup_tool to retrieve their supervisor’s details. 5. Provide the supervisor's contact information and recommend them as the best next point of contact.

The steps

  1. When clicking ‘Test workflow’
  2. Default Data Loader
  3. Embeddings OpenAI
  4. Recursive Character Text Splitter
  5. Window Buffer Memory
  6. OpenAI Chat Model
  7. Vector Store Tool
  8. OpenAI Chat Model1
  9. Embeddings OpenAI1
  10. Employee Lookup Tool
  11. OpenAI Chat Model2
  12. OpenAI Chat Model3
  13. OpenAI Chat Model4
  14. Auto-fixing Output Parser

39 steps in total.

Similar automations