Connect AI Studio to On-Prem SQL Server (No Open Ports)

Connect Google AI Studio to an on-prem SQL Server database without opening a single firewall port or handing over a database password.

In this video I put DreamFactory in front of a SQL Server database on my local network, generate a REST API from it, lock that API down with a read-only role and a scoped API key, then I have AI Studio build a live delivery operations dashboard on top of it. AI Studio calls the API from its own Node server, so the key never reaches the browser.

What's covered:

  • Why AI app builders like AI Studio can't reach on-prem databases, and how DreamFactory bridges that gap over HTTPS
  • Connecting SQL Server in DreamFactory and generating a REST API with no code
  • Testing the API live in the API docs, including filters that run as SQL on the server
  • Creating a read-only role scoped to specific tables
  • Creating an API key tied to that role: the only credential AI Studio ever holds
  • Connecting AI Studio to the API with the key kept server-side
  • A live dashboard over 2 million shipments: KPI cards, delivery center filter, late deliveries, tracking number search

Timestamps:

0:00 Intro and architecture

0:20 SQL Server connection in DreamFactory

1:33 Live API docs and filters

2:41 Read-only role

4:24 Scoped API key

5:13 The AI Studio prompt, explained

6:43 AI Studio builds the app (25x)

7:00 Adding the secrets

7:34 Live dashboard on on-prem data

7:48 Tracking number search

8:15 Wrap-up

#DreamFactory #GoogleAIStudio #Gemini #SQLServer #RESTAPI #OnPrem #AIAppBuilder #Dashboard #APISecurity