# ignite25-LAB512-prototyping-multimodal-agents-with-azure-ai-foundry-and-the-ai-toolkit **Repository Path**: mirrors_microsoft/ignite25-LAB512-prototyping-multimodal-agents-with-azure-ai-foundry-and-the-ai-toolkit ## Basic Information - **Project Name**: ignite25-LAB512-prototyping-multimodal-agents-with-azure-ai-foundry-and-the-ai-toolkit - **Description**: No description available - **Primary Language**: Unknown - **License**: CC-BY-SA-4.0 - **Default Branch**: main - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2025-10-01 - **Last Updated**: 2025-10-04 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # [Microsoft Ignite 2025](https://ignite.microsoft.com) ## π₯LAB512: Prototyping multimodal agents with Azure AI Foundry and the AI Toolkit [](https://discord.com/invite/ByRwuEEgH4) [](https://aka.ms/foundry/forum) ### Session Description In this lab, you'll get hands-on with the AI Toolkit (AITK) and Azure AI Foundry in VS Code to explore and compare the latest multimodal and reasoning models from the Model Catalog. Learn how to augment models for a real-world business scenario, using prompt and context engineering. Prototype an agent using the AITK Agent Builder, and equip the agent with the right tools via MCP. ### π§ Learning Outcomes By the end of this session, learners will be able to: - Explore and compare models to select the best fit for their business scenario - Augment models with prompts and data to get more accurate and grounded responses - Prototype an agent by combining models and instructions with tools via MCP (Model Context Protocol) ### π» Technologies Used 1. AI toolkit in Visual Studio Code 1. GitHub-hosted and Azure AI Foundry-hosted models 1. MCP servers ### π Microsoft Learn MCP Server [](https://vscode.dev/redirect/mcp/install?name=microsoft.docs.mcp&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Flearn.microsoft.com%2Fapi%2Fmcp%22%7D) The Microsoft Learn MCP Server is a remote MCP Server that enables clients like GitHub Copilot and other AI agents to bring trusted and up-to-date information directly from Microsoft's official documentation. Get started by using the one-click button above for VSCode or access the [mcp.json](.vscode/mcp.json) file included in this repo. For more information, setup instructions for other dev clients, and to post comments and questions, visit our Learn MCP Server GitHub repo at [https://github.com/MicrosoftDocs/MCP](https://github.com/MicrosoftDocs/MCP). Find other MCP Servers to connect your agent to at [https://mcp.azure.com](https://mcp.azure.com). *Note: When you use the Learn MCP Server, you agree with [Microsoft Learn](https://learn.microsoft.com/en-us/legal/termsofuse) and [Microsoft API Terms](https://learn.microsoft.com/en-us/legal/microsoft-apis/terms-of-use) of Use.* ### π Resources and Next Steps | Resources | Links | Description | |:-------------------|:----------------------------------|:-------------------| | Ignite 2025 Next Steps | [https://aka.ms/Ignite25-Next-Steps](https://aka.ms/Ignite25-Next-Steps?ocid=ignite25_nextsteps_cnl) | Links to all repos for AI Tour 26 Sessions | | Azure AI Foundry Community Discord | [](https://discord.com/invite/ByRwuEEgH4)| Connect with the Azure AI Foundry Community! | | Learn at Ignite | [https://aka.ms/LearnAtIgnite](https://aka.ms/LearnAtIgnite?ocid=ignite25_nextsteps_github_cnl) | Continue learning on Microsoft Learn | ## Content Owners
![]() Carlotta Castelluccio π’ |
![]() April Gittens π’ |