---
title: "Securely Using LLMs With Your Own Data | DreamFactory"
description: "The case for putting a governed layer between a language model and your database: exposing data to AI clients, tools and agents under role-based access…"
url: "https://www.dreamfactory.com/videos/securely-use-llms-with-your-data"
---

[Home](https://www.dreamfactory.com/) › [Videos](https://www.dreamfactory.com/videos) › Securely Using LLMs With Your Own Data

# Securely Using LLMs With Your Own Data

Video·9 July 2025·7 min 12 sec

The case for putting a governed layer between a language model and your database: exposing data to AI clients, tools and agents under role-based access control and fine-grained, zero-trust rules rather than handing over a connection string. This is the thinking behind the AI Data Gateway, which now ships as part of the platform.

## What you’ll learn

* Why an LLM should never hold a database credential
* RBAC-protected, zero-trust exposure of specific datasets
* The design behind the AI Data Gateway

[Book a Demo](https://www.dreamfactory.com/demo)[More on our YouTube channel](https://www.youtube.com/@DreamfactoryAPI)

## More videos

* [DreamFactory as an AI Gateway](https://www.dreamfactory.com/videos/dreamfactory-as-ai-gateway)
* [Securely Exposing Data to LLMs Over MCP](https://www.dreamfactory.com/videos/mcp-expose-data-to-llms)
* [DreamFactory MCP for Enterprise AI](https://www.dreamfactory.com/videos/mcp-explainer-enterprise-ai)
* [Instantly Generate a REST API for Snowflake](https://www.dreamfactory.com/videos/snowflake-rest-api)

[Browse all videos ›](https://www.dreamfactory.com/videos)

Video: https://www.youtube.com/watch?v=RbXK_9udisU