Run fast AI inference with Groq

Databases
Fast AI inference platform
Overview

The Jet Admin Groq integration lets your app send prompts to Groq's fast inference API and read the response back into your own records, driven by the same tables, forms and record actions you already build in Jet. Whether a chat interface needs a near-instant reply, a call needs transcribing, or a high volume of tickets needs routing in real time, the whole workflow runs inside Jet, and every call is scoped by role and written to the audit log.

That covers what teams build on Groq first: chat-style screens where responses stream back fast enough to feel live, transcription workflows for calls and voice notes, and high-volume triage that classifies incoming records in real time. Because Jet reads your own database alongside Groq, every prompt can pull in the exact record it's working on, and every response writes straight back to it.

What you can do
Generate text completion
Send a prompt built from your own record data to a Groq-hosted model and write the fast response back to the record.
Transcribe audio
Send an audio file to Groq's Whisper endpoint and write the transcript back to the record it belongs to.
Classify or tag content
Send text to Groq and use the response to set a category, priority or sentiment field on a record automatically.
Summarize text
Send a document or ticket thread to Groq and store a short summary next to the record, returned in under a second.
Stream a response
Stream a Groq completion token by token into a live screen, for a chat-style interface built on your own data.
Use Cases
Scenario
What it looks like
Real-time chat interface
Build a chat-style screen backed by your own data where responses stream back fast enough to feel instant.
Live call or meeting transcription
Transcribe a call or voice note the moment it's uploaded and attach the text to the record it belongs to.
Automated data enrichment
Classify, tag or summarize incoming records the moment they're created, at a speed that keeps up with high record volume.
High-volume support triage
Classify and route large volumes of incoming tickets or requests in real time, without queuing behind a slower model.

Key benefits

  • Near-instant responses. Get completions back fast enough for a live chat interface, not just a background job.
  • Prompts built from your own data. Pull fields from a record straight into a prompt, instead of copying and pasting between tools.
  • Results written back automatically. Store a completion, summary or extracted field directly on the record it came from.
  • Actions with a record. Every Groq call runs inside your app, scoped by role, and written to the audit log.
  • Complete workflows. Tie a generated result to everything that follows it: update a record, trigger a notification, route for review.
  • Built-in transcription. Turn a call or voice note into text without a separate transcription service.

How to connect Jet Admin with Groq

  1. In Groq, open console.groq.com and create an API key.
  2. In Jet Admin, open your project and add a new resource, or pick Groq while creating a project.
  3. Choose Groq and paste the API key.
  4. Jet loads the Groq actions available: completions, streaming and audio transcription.
  5. Add the data sources you want to feed into prompts.
  6. Generate the screens you need, then set role permissions on who can trigger AI actions.
  7. Add actions and workflows on top: live chat interfaces, call transcription, and real-time ticket routing.