How to get started with an AI template

This article provides instructions on how to use an AI template to get started with Microsoft Foundry.

Get started with an AI template

This article refers to the Microsoft Foundry (new) portal.

Find, explore, and deploy AI solution templates from the Foundry portal.

Streamline your code-first development with prebuilt, task-specific Azure AI templates. These ready-to-use, customizable templates help you skip setup, reduce friction, and deliver value faster with trusted, scalable infrastructure. Built on insights from over 2,000 customer engagements, AI solution templates significantly reduce time from concept to production at scale.

AI solution templates include customizable code samples, pre-integrated Azure services, and GitHub-hosted quick-start guides. Development teams can focus on outcomes instead of setup, building solutions for popular use cases like live voice agents, release management, and data unification.

These templates harness the power of multi-agent, agentic AI, enabling you to automate workflows, optimize operations, reduce costs, and make faster, data-driven decisions.

Starter templates, manifests, code samples, and other resources made available by Microsoft or its partners (“samples”) are designed to assist in accelerating development of agents and AI solutions for specific scenarios. Review all provided resources and carefully test output behavior in the context of your use case. AI responses might be inaccurate and AI actions should be monitored with human oversight. Learn more in the transparency documents for Agent Service and Agent Framework.

Agents and AI solutions you create might be subject to legal and regulatory requirements, might require licenses, or might not be suitable for all industries, scenarios, or use cases. By using any sample, you acknowledge that Agents, AI solutions, or other output created using those samples are solely your responsibility, and that you will comply with all applicable laws, regulations, and relevant safety standards, terms of service, and codes of conduct.

Available templates:

Template	Popular customer use cases
Get started with AI chat	Build interactive chat applications Baseline Microsoft Foundry chat reference architecture
Get started with AI agents	Create autonomous AI agents
Build agentic apps to unify data	Embed analytics across applications with instant data visualization for: • Sales performance analysis • Customer insights and reporting • Natural language analysis on structured data
Create a multi-agent release manager assistant	Enable AI-powered release planning for: • Cross-system release coordination • Real-time dependency mapping and release health assessment • Advanced visualization for retrieved insights • Safe update mechanisms built into AI agents
Create a call center voice agent	Develop interactive voice agents for: • Customer support • Product catalog navigation • Self-service solutions
Unlock insights from conversational data	Extract knowledge from conversations Build a conversation knowledge mining solution
Multi-agent workflow automation	Automate complex workflows Build a multiple-agent workflow automation solution
Multi-modal content processing	Process diverse content types Extract and map information from unstructured content
Generate documents from your data	Create documents automatically Build a document generation system
Improve client meetings with agents	Enhance meeting productivity
Modernize your code with agents	Update legacy code
Build your conversational agent	Create conversational experiences
Retrieve and summarize SharePoint data	Retrieve content from SharePoint sites

Each template includes a GitHub README with setup, deployment, and customization instructions. Start there for the fastest path forward.

Prerequisites

• An Azure account with an active subscription. If you don’t have one, create a free Azure account, which includes a free trial subscription.

• Appropriate RBAC role to create Foundry resources. For details, see Role-based access control.

• A Foundry project.

Benefits of AI solution templates

AI templates in Microsoft Foundry provide:

• Faster time-to-value: Skip boilerplate code and infrastructure setup to move from concept to production quickly.
• Reduced engineering overhead: Preintegrated Azure services eliminate deployment friction.
• Trusted infrastructure: Build with confidence on Microsoft’s secure, scalable AI platform.
• Modular and interoperable foundation: Scale solutions efficiently across your organization.
• Best practices built-in: Leverage proven patterns and frameworks from thousands of customer engagements.

Start with a sample application

Sign in to Microsoft Foundry. Make sure the New Foundry toggle is on. These steps refer to Foundry (new).

1. Open your project.

2. On the left pane, select Templates.

3. Find the solution template you want to use.

4. Select Open in Github to view the entire sample application.

5. In some cases, you can also view a step-by-step tutorial that explains the AI code. ::: moniker-end

::: moniker range=“foundry” Sign in to Microsoft Foundry. Make sure the New Foundry toggle is on. These steps refer to Foundry (new).

1. Select Discover from the upper-right navigation.
2. Select Solution templates from the left pane.
3. Select Open in Github to view the entire sample application.
4. In some cases, you can also view a step-by-step tutorial that explains the AI code.

::: moniker-end

Explore the sample application

When you view the GitHub repository for your sample, check the README for more instructions and information on how to deploy your own version of the application.

Instructions vary by sample, but most include how to:

• Open the solution in the location of your choice:
  • GitHub Codespaces
  • VS Code Dev Containers
  • Your local IDE
• Deploy the application to Azure
• Test the application

The README also includes information about the application, such as the use case, architecture, and pricing information.

Deploy templates quickly

By using the quick-deploy options, you can launch any Foundry template in minutes. These architectures and implementations are customizable while staying Well-Architected Framework (WAF) aligned by using Azure Verified Modules. Use tools such as PSRule and TFlint to test that your modified implementation is production-ready.

Next step

• Quickstart: Get started with Foundry