Agent Landing Zone

Secure, enterprise-ready landing zone for deploying AI agent applications on Microsoft Foundry.

[!NOTE] GPT-RAG has evolved into Agent Landing Zone. Same project, broader scope: infrastructure and applications for enterprise agents on Azure. For Agent Landing Zone, use the current documentation. For older GPT-RAG deployments, refer to the legacy documentation.

Architecture

Standalone reference architecture for private-network deployments. Resource selection and reuse depend on deployment settings. Select the image to open the full-resolution PNG. For Platform Hub and AI Gateway combinations, see the reference architectures.

Deploy

• Full stack — Deploy the infrastructure and default agent application.
• Infrastructure only — Provision the foundation without deploying application images.
• Custom applications — Deploy your own application on the foundation.

Components

Component versions for this release are pinned in manifest.json.

Component	Repository
UI	Azure/agent-app-ui
Orchestrator	Azure/agent-app-orchestrator
Ingestion (optional)	Azure/agent-app-ingestion
Agent App MCP Server (optional)	Azure/agent-app-mcp

Start with the Agent Application guide for component selection and first use. The MCP guide covers server setup and onboarding its current NL2SQL tools.

Documentation

The full documentation lives in the Agent Landing Zone section of the AI Landing Zones documentation site.

Contributing

See CONTRIBUTING.md, SECURITY.md, and SUPPORT.md. Release history is in CHANGELOG.md.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos is subject to those third-party's policies.