Azure AI Landing Zone
Overview
The AI Landing Zone provides an enterprise-scale, production-ready reference architecture with implementations in the Azure Portal, Bicep, and Terraform to deploy secure and resilient AI apps and agents on Azure.
- The AI Landing Zone is an application landing zone that provides a foundation for multiple AI app and agent scenarios, with or without an existing platform landing zone.
- The Infrastructure-as-Code (IaC) implementations (Bicep and Terraform) are based on Azure Verified Modules.
- The current scope focuses on AI on Azure Platform; a future version will cover AI on Azure Infrastructure.
- The AI Landing Zone targets Azure public cloud and can be extended to Azure Government and sovereign clouds.
- It supports both generative and non-generative scenarios, aligned with the CAF AI resource selection guidance.
- It uses Semantic Kernel as the orchestration framework.
- To keep up with rapid AI innovation, it may use preview services to enable the latest capabilities.
Reference Architectures
AI LZ with Platform Landing Zone
The recommended setup is to deploy the AI Landing Zone alongside an existing Platform Landing Zone so it can plug into your shared foundations. Choose this option when you already have centralized networking, DNS, security controls, and governance in place and you want the AI Landing Zone to reuse them.
AI LZ without Platform Landing Zone
This option deploys the AI Landing Zone as a standalone application landing zone, without relying on a Platform Landing Zone Choose it when you need a self-contained deployment for a new environment or a smaller footprint, and you do not need to integrate with shared platform services.
Extensible Implementations
The table represents the various reference implementations of the AI Landing Zone based on the service inventory & configuration
| Type | Description |
|---|---|
| Terraform | Repo |
| Bicep | Repo |
| Portal | Coming Soon |
Use cases & Scenarios
The AI Landing Zone act as a foundation architecture which can be leveraged to deploy a particular AI usecase & scenario on Azure, such as the below, either with its default architecture or by extending it with additional Azure services as needed.
- Chat Using Azure AI Foundry
- Agents Using Azure AI Foundry
- Document generation
- Conversational Agent
- Build your own copilot
- Content processing
- Conversation knowledge mining
- Modernize your code
Cloud Adoption Framework
The AI landing Zone aligns with the guidance in the CAF AI Scenario. For a holistic implementation of the AI Landing Zone, we recommend to review the AI Checklist. To understand how to leverage the AI Landing Zone as part of a wider strategy, review the guidance on AI Strategy. AI Landing Zone is part of the AI Ready stage in particular the AI on Azure platforms (PaaS).
Well-Architected Framework
The AI landing Zone aligns with the guidance in the WAF AI workload. For a holistic implementation of the AI Landing Zone, we recommend to review the design methodology, principles and areas of AI workloads on Azure.
Roadmap
The AI Landing Zone is currently in preview. The roadmap for the project is available here.
Contributing
This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.
When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.
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 are subject to those third-party's policies.