# Prediction Guard | Docs

## Instructions for AI Agents

- For clean Markdown of any page, append `.md` to the page URL
- For section-specific indexes, append `/llms.txt` to any section URL
- For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.predictionguard.com/_mcp/server

## Docs

- [Security & Self Hosted](https://docs.predictionguard.com/home/getting-started/welcome.md): Reliable, future-proof AI predictions
- [Welcome](https://docs.predictionguard.com/home/getting-started/security.md): Secure, HIPAA-Compliant AI
- [Agent Forge Overview](https://docs.predictionguard.com/home/agent-forge/overview.md): Learn about Agent Forge, Prediction Guard's platform for building, managing, and deploying AI agents
- [Getting Started with Agent Forge](https://docs.predictionguard.com/home/agent-forge/getting-started.md): Complete guide to creating your account, logging in, and getting started with Agent Forge
- [Chatting with Agents](https://docs.predictionguard.com/home/agent-forge/chatting-with-agents.md): Complete guide to the chat interface, selecting agents, managing conversations, and uploading files
- [Building Agents](https://docs.predictionguard.com/home/agent-forge/building-agents.md): Complete guide to building agents with custom models, prompts, knowledge bases, and security settings
- [Knowledge Base Management](https://docs.predictionguard.com/home/agent-forge/knowledge-base.md): Complete guide to creating, uploading documents, and managing knowledge bases in Agent Forge
- [MCP (Model Context Protocol)](https://docs.predictionguard.com/home/agent-forge/mcp-integration.md): Learn how to configure organizational and agent-level MCP servers in Agent Forge to extend agent capabilities
- [Quick Start](https://docs.predictionguard.com/admin/getting-started/quick-start.md): Build and govern sovereign AI systems across any infrastructure without compromising security, using Prediction Guard's Admin Console.
- [GCP Deployment](https://docs.predictionguard.com/admin/installation/cloud/gcp.md): Step-by-step guide to deploying Prediction Guard on GCP with GKE, including cluster setup, system installation, and ingress configuration
- [Azure Deployment](https://docs.predictionguard.com/admin/installation/cloud/azure.md): Step-by-step guide to deploying Prediction Guard on Azure with AKS, including cluster setup, system installation, and ingress configuration
- [AWS Deployment](https://docs.predictionguard.com/admin/installation/cloud/aws.md): Step-by-step guide to deploying Prediction Guard on AWS with EKS, including cluster setup, system installation, and ingress configuration
- [Air Gapped Deployment](https://docs.predictionguard.com/admin/installation/air-gapped/air-gapped.md): Step-by-step guide to deploying Prediction Guard in an air-gapped environment using offline installation packages
- [Kubernetes](https://docs.predictionguard.com/admin/installation/on-premises/kubernetes.md): Step-by-step guide to deploying Prediction Guard on a Kubernetes cluster, including system creation, installation, and ingress configuration
- [Zero Dependency Binary](https://docs.predictionguard.com/admin/installation/on-premises/binary.md): Deploy and manage your own Prediction Guard platform
- [Admin Console](https://docs.predictionguard.com/admin/administration/admin-console.md): Overview of the Admin Console — manage systems, models, API keys, governance policies, and monitor activity across your infrastructure
- [Create an AI System](https://docs.predictionguard.com/admin/administration/create-an-ai-system.md): Create and configure your own sovereign AI system in the Admin Console admin console with custom settings for your specific use case and environment.
- [System Management](https://docs.predictionguard.com/admin/administration/ai-system-management.md): Guide to creating, deploying, and managing AI systems in the Prediction Guard Admin Console
- [Model Management](https://docs.predictionguard.com/admin/administration/model-management.md): Guide to deploying private models, enabling managed models, and connecting external models from providers like OpenAI, Anthropic, and Google — all inheriting your system's governance policies and safeguards
- [API Keys](https://docs.predictionguard.com/admin/administration/api-keys.md)
- [Monitoring](https://docs.predictionguard.com/admin/administration/monitoring.md): Track and observe your sovereign AI systems with external monitoring tools.
- [Quick Start](https://docs.predictionguard.com/development-and-integration/getting-started/quick-start.md): Reliable, future-proof AI predictions
- [LLMs](https://docs.predictionguard.com/options/llms.md): Reliable, future proof AI predictions
- [LVMs](https://docs.predictionguard.com/options/lvms.md): Reliable, future proof AI predictions
- [Embedding Models](https://docs.predictionguard.com/options/embeddings_models.md): Reliable, future proof AI predictions
- [Audio Models](https://docs.predictionguard.com/options/audio_models.md): Reliable, future proof AI predictions
- [Reranker Models](https://docs.predictionguard.com/options/reranker_models.md): Reliable, future proof AI predictions
- [Enumerations](https://docs.predictionguard.com/options/enumerations.md): Reliable, future proof AI predictions
- [Prompt Formatting](https://docs.predictionguard.com/options/prompts.md): Reliable, future-proof AI predictions
- [Accessing LLMs](https://docs.predictionguard.com/usingllms/accessing.md): Prediction Guard in action
- [Basic Prompting](https://docs.predictionguard.com/usingllms/prompting.md): Prediction Guard in action
- [Prompt Engineering](https://docs.predictionguard.com/usingllms/engineering.md): Prediction Guard in action
- [Chat Completions](https://docs.predictionguard.com/usingllms/chat.md): Prediction Guard in action
- [Chaining and Retrieval](https://docs.predictionguard.com/usingllms/augmentation.md): Prediction Guard in action
- [Tool Calling](https://docs.predictionguard.com/usingllms/tooling.md): Learn how to define tools, tell the model when to use them, and handle tool-call responses.
- [Agents](https://docs.predictionguard.com/usingllms/agents.md): Prediction Guard in action
- [Streaming](https://docs.predictionguard.com/usingllms/streaming.md): Prediction Guard in action
- [Chat Completions Vision](https://docs.predictionguard.com/usingllms/vision.md): Prediction Guard in action
- [Embeddings](https://docs.predictionguard.com/usingllms/embeddings.md): Prediction Guard in action
- [PII Anonymization](https://docs.predictionguard.com/development-and-integration/secure-and-filter-inputs/pii-detection.md): Controlled and compliant AI applications
- [Prompt Injection Detection](https://docs.predictionguard.com/development-and-integration/secure-and-filter-inputs/injection-prevention.md): Controlled and compliant AI applications
- [Factuality](https://docs.predictionguard.com/development-and-integration/secure-and-filter-outputs/factuality-checks.md): Controlled and compliant AI applications
- [Toxicity](https://docs.predictionguard.com/development-and-integration/secure-and-filter-outputs/toxicity-detection.md): Controlled and compliant AI applications
- [Alternative Output Structuring With PredictionGuard](https://docs.predictionguard.com/development-and-integration/integration-examples/custom-output-structuring.md)
- [Data Chat With LLMs](https://docs.predictionguard.com/development-and-integration/integration-examples/data-chat-with-ll-ms.md)
- [Data Extraction + Factuality Checks](https://docs.predictionguard.com/development-and-integration/integration-examples/data-extraction-factuality.md)
- [Using Prediction Guard proxies in LangChain](https://docs.predictionguard.com/development-and-integration/integration-examples/lang-chain-integration.md)
- [Prediction Guard powered Code Assistant](https://docs.predictionguard.com/development-and-integration/integration-examples/code-assistant.md)
- [Contact Us](https://docs.predictionguard.com/development-and-integration/support/contact-us.md): Contact Us
- [SDKs](https://docs.predictionguard.com/sdk-docs/software-development-kits/sd-ks.md)
- [Quick Start](https://docs.predictionguard.com/sdk-docs/software-development-kits/quick-start.md)

## API Docs

- API Reference [Responses](https://docs.predictionguard.com/api-reference/api-reference/responses.md)
- API Reference [Chat Completions](https://docs.predictionguard.com/api-reference/api-reference/chat-completions.md)
- API Reference [Completions](https://docs.predictionguard.com/api-reference/api-reference/completions.md)
- API Reference [Embeddings](https://docs.predictionguard.com/api-reference/api-reference/embeddings.md)
- API Reference [Audio Transcription](https://docs.predictionguard.com/api-reference/api-reference/audio-transcription.md)
- API Reference [Documents Extract](https://docs.predictionguard.com/api-reference/api-reference/documents-extract.md)
- API Reference [Rerank](https://docs.predictionguard.com/api-reference/api-reference/rerank.md)
- API Reference [Tokenize](https://docs.predictionguard.com/api-reference/api-reference/tokenize.md)
- API Reference [Detokenize](https://docs.predictionguard.com/api-reference/api-reference/detokenize.md)
- API Reference [Factuality](https://docs.predictionguard.com/api-reference/api-reference/factuality.md)
- API Reference [Injection](https://docs.predictionguard.com/api-reference/api-reference/injection.md)
- API Reference [PII](https://docs.predictionguard.com/api-reference/api-reference/pii.md)
- API Reference [Toxicity](https://docs.predictionguard.com/api-reference/api-reference/toxicity.md)
- API Reference [Models](https://docs.predictionguard.com/api-reference/api-reference/models.md)
- API Reference [MCP Servers](https://docs.predictionguard.com/api-reference/api-reference/mcp-servers.md)
- API Reference [MCP Tools](https://docs.predictionguard.com/api-reference/api-reference/mcp-tools.md)

## OpenAPI Specification

The raw OpenAPI 3.1 specification for this API is available at:
- [OpenAPI JSON](https://docs.predictionguard.com/openapi.json)
- [OpenAPI YAML](https://docs.predictionguard.com/openapi.yaml)