For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Contact usJoin our Discord
HomeAdministration & GovernanceDevelopment and IntegrationAgent ForgeAPI ReferenceSDK Docs
HomeAdministration & GovernanceDevelopment and IntegrationAgent ForgeAPI ReferenceSDK Docs
  • Getting Started
    • Welcome
    • Security
  • Agent Forge
    • Overview
    • Getting Started
    • Chatting with Agents
    • Building Agents
    • Knowledge Base
    • MCP Integration
LogoLogo
Contact usJoin our Discord
Built with
Administration & Governance

Build and govern sovereign AI systems across any infrastructure without compromising security, using Prediction Guard’s Admin Console.

Get Started →
Development and Integration

Understand how to use our API on a deeper level. Learn how to use our different endpoints and features.

Get Started →
Agent Forge

Build and deploy AI agents without code. Create specialized assistants with knowledge bases, security controls, and custom configurations.

Get Started →
API Reference

Integrate compliant natural language processing and generation into your products with a few lines of code.

Get Started→
SDK Documentation

We provide official open-source SDKs (client libraries) for your favorite platforms. These clients make connecting to our API faster and help avoid errors.

Get Started →

Compliance, Security, and Self Hosting

We don’t store, log, or cache any prompt data flowing through our system. We couldn’t train models on your data if we wanted to! Our focus is keeping your data your data.

Get Started →


About Us


Prediction Guard allows you to integrate secure, private GenAI functionality into your software applications via an easy-to-use API. The API can be self-hosted or accessed via our managed cloud offering. These docs are relevant to both the self-hosted and managed cloud offerings (although a self-hosted installation might have a variety of custom models deployed that are not listed throughout these docs).


Our endpoints offer different ways to interact with our models and offer additional value on top of them. From PII protection to Toxicity checks we can help you utilize AI in a safe and compliant way.

/EMBEDDINGS →

/INJECTION →

/FACTUALITY →

/TOXICITY →

/PII →


Schedule a demo with our team!

Learn More