Social messages get sorted, and you approve each reply with a tap

AI splits your Facebook Graph API inbox into leads, questions and spam, drafts a reply and sends it to Twake for your approval. Everything is logged in Microsoft SharePoint.

  • AI separates leads and questions from spam
  • The reply is drafted for you but only sends on your OK
  • Approve with a tap in Twake
  • Every message and its outcome lands in Microsoft SharePoint
Set it up for yourselfScriptera

How it works

To pass leads from Twake to Facebook Graph API automatically, use a ready-made scenario — no manual copying, no lost leads.

  1. Starts when: Error Handler Trigger
  2. Then: Slack: Send Error Alert
  3. Starts when: Trigger – Fetch New Facebook Messages (Every Hour)
  4. Then: Fetch Facebook Conversations (Graph API)
  5. Then: Format Incoming Message Data
  6. Then: AI – Classify Message (Lead / Query / Spam)
  7. Check: Route Messages by Category
  8. If yes: Slack Approval – Lead Message
  9. Check: Check Lead Approval Status
  10. If yes: Send AI Reply – Lead Approved
  11. Then: Log to Google Sheets – Lead Approved
  12. If no: Send Fallback Reply – Lead Rejected
  13. Then: Log to Google Sheets – Lead Rejected
  14. If no: Slack Approval – Query Message
  15. Check: Check Query Approval Status
  16. If yes: Send AI Reply – Query Approved
  17. Then: Log to Google Sheets – Query Approved
  18. If no: Send Fallback Reply – Query Rejected
  19. Then: Log to Google Sheets – Query Rejected
  20. If no: Log to Google Sheets – Spam Messages
  21. Then: Model – GPT-4 Language Model
  22. Then: Parse AI Output (JSON Parser)
  23. Then: Memory – Conversation Context Buffer

You can launch this Twake + Facebook Graph API integration in Scriptera: describe the task in plain words — the scenario is built, launched and monitored for you.

Similar scenarios