Taxi order intake through chat — with validation and driver matching

A client leaves a request in chat — AI parses it, records the order in Metabase, matches an active driver (with Supabase fast memory) and returns a validated response.

  • Requests are parsed and validated without a dispatcher
  • A driver is matched automatically, from the active ones
  • Fast Supabase memory speeds up repeat lookups
  • Orders are neatly recorded in Metabase
Postgres Tool
Set this upScriptera

How it works

To connect Metabase and Supabase, you don't need a developer: a ready-made scenario links them in minutes.

  1. Starts when: Flow Trigger
  2. Then: Input
  3. Then: Provider Cache
  4. Check: Provider Cache Switch
  5. If yes: Parse Provider
  6. Then: Provider
  7. Then: Provider Number
  8. Then: AI Agent
  9. Then: Code
  10. Check: If Valid?
  11. If yes: If Score
  12. If yes: Output w/ Score
  13. Then: Call Back
  14. If no: Output w/o Score
  15. If no: Test Output
  16. Then: Error Output1
  17. If no: Load Provider Data
  18. Check: If Active
  19. If yes: Save Provider Cache
  20. Starts when: Test Trigger
  21. Then: Test Fields
  22. Then: xAI @grok-2-1212
  23. Then: Create Booking Data
  24. Then: Calculator

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

Similar scenarios