In-stock replies to DMs — on their own

The scenario reads questions from Facebook Graph API, an AI checks them against stock in Stackby, and replies to the customer in the same conversation — in stock or not.

  • In-stock answer in seconds
  • Stock checked without manual matching
  • Works around the clock
  • Edge-case messages sent for review
Set it up for yourselfScriptera

How it works

To move data from talantix to Facebook Graph API automatically, use a ready-made scenario — no manual exports.

  1. Starts when: Trigger – Fetch New Facebook Messages (Every Hour)
  2. Then: Fetch Facebook Conversation List
  3. Then: Fetch Facebook Conversation Messages
  4. Check: Validate Record Structure
  5. If yes: Extract Latest Facebook Message
  6. Then: AI – Extract Product & Customer Intent
  7. Check: Merge AI Output With Inventory Dataset
  8. Then: Build Combined AI + Inventory Payload (
  9. Then: AI – Match Requested Product in Inventory
  10. Then: Parse AI Product Match JSON
  11. Check: Check If Product Exists
  12. If yes: Send Facebook Reply — Product Found
  13. If no: Send Facebook Reply — Product Not Found
  14. Then: Fetch Inventory Records from Airtable
  15. If no: Log Invalid Records to Google Sheet
  16. Then: Configure GPT-4o — Message Classification Model
  17. Then: Configure GPT-4o — Product Matching Model

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

Similar scenarios