Voice answers to inbound calls, straight from your own documents

Each night the scenario turns documents from Databricks into a meaning-searchable base in Webflow, then answers inbound calls by voice — strictly from what it finds in your own materials.

  • Answers come from your documents, not from thin air
  • The base refreshes nightly — the documents are always current
  • Search works by meaning, not exact keyword matching
  • A human is only needed for the hard cases
Default Data LoaderEmbeddings OpenAISupabase Vector StoreWebhookGoogle
Set it up for yourselfScriptera

How it works

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

  1. Starts when: Täglich 02:00 Uhr – Auto-Reindex
  2. Then: Google Drive – Dateien auflisten
  3. Check: Loop – Jede Datei
  4. Then: Supabase – Chunks speichern
  5. Then: Datei-IDs extrahieren
  6. Then: Google Drive – Datei herunterladen
  7. Starts when: Manueller Start – Reindex
  8. Then: Text Loader
  9. Then: OpenAI Embeddings – Indexierung
  10. Starts when: Placetel – Webhook Eingang
  11. Then: Question and Answer Chain
  12. Starts when: Placetel – Antwort zurückgeben
  13. Then: OpenAI Embeddings – Abfrage
  14. Then: Vector Store Retriever
  15. Then: Supabase Vector Store
  16. Then: Groq Chat Model

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

Similar scenarios