Microsoft AI Tour resources

Build and ship AI agents faster with GitHub Models and Azure. Prototype with open models, scale with Azure AI Foundry models, and streamline workflows using the AI Toolkit in VS Code. Experiment with models and prompts, evaluate agent responses, then move from prototype to cloud with cutting-edge developer tools.

See how GitHub Copilot acts as an AI agent in real-world development workflows—planning, executing multi-step tasks, and integrating seamlessly into engineering processes. Discover how Copilot can boost team productivity, accelerate software development, and support best practices. Go beyond autocomplete with practical, real-world examples that demonstrate measurable impact within your organization.

In this session, we put the spotlight on model customization. Learn what your options are, and why fine-tuning might be the right option for your scenario. Learn about the various fine-tuning options in Azure AI Foundry, and build your intuition for using techniques like Distillation (for reducing cost) and RAFT (for improving precision) with hands-on demos. Walk away with resources and insights that help you streamline your end-to-end model optimization journey with Azure AI Foundry.

Learn how to build production-ready AI agents using Azure AI Search and PostgreSQL. This session covers agentic retrieval, graph-based retrieval, and advanced grounding techniques to power your enterprise AI apps.

The solution demonstrates patterns for designing, implementing, and deploying multi-service AI agents with governance, reuse, and responsible-AI considerations.

BRK-447 demonstrates how to use GitHub Copilot inside Visual Studio to accelerate development, augment Copilot with MCP servers for documentation-aware suggestions, and employ Copilot Agents to automate issue-driven code changes and UI updates. The session mixes short live demos with recorded segments for longer or fragile flows.

This session explores how organizations can enable agentic AI applications by unifying their data estate using Microsoft Fabric. Through the story of Zava, a regional DIY retailer, the session demonstrates how fragmented data systems can be modernized, integrated, and made AI-ready. Attendees will see practical demos covering data unification, transformation, governance, CI/CD for data products, and the integration of AI-powered experiences, all while maintaining robust security and compliance.

In this session you'll learn how to use AI enabled administrative tools to perform common IT Operations tasks in your Azure environment.

In this session, you'll learn how to integrate AI in your solutions and tackle common problems like scaling, caching and security. You'll also learn how to standardize when building with Agents by using Model Context Protocol, MCP.

Building generative AI apps starts with model selection—but earning user trust requires continuous evaluation. In this talk, learn how Azure AI Evaluations SDK helps assess models pre- and post-production, analyze results, and improve quality through Observability.

In this talk, discover how the Model Context Protocol (MCP) is transforming the way AI agents connect with tools, data and each other in a standardized way and is becoming part of the Microsoft ecosystem, whether you're working in Azure AI Foundry, Copilot Studio or GitHub Copilot. MCP is more than a protocol—it’s the connective tissue for building intelligent, interoperable systems. You’ll get a fast-paced, hands-on introduction to MCP fundamentals, then dive into building your own MCP server, using it in VS Code as the host and GitHub Copilot as the client.

As 85% of enterprises embrace multi-model AI strategies, developers face growing complexity in selecting, deploying, and managing the right models for each task. In this session, discover how the model router in Azure AI Foundry intelligently automates model selection based on performance, cost, and latency. This intelligent orchestration layer reduces operational overhead, accelerates deployment, and unlocks scalable AI operations across your organization. Say goodbye to model fatigue and let the router do the strategic lifting.

Did you try out the AI Tour Advisor at the community booth? In this talk, we’ll break down how the agent is built and dive into the technology used under the hood. We’ll cover everything from instructions and models to tools and function calling, and explore how the entire experience comes together through the interface and agent framework.

Prepping data shouldn’t feel like a chore. See how multi-cloud OneLake shortcuts connect to data sources without duplication, run shortcut file transforms and shortcut AI transforms like summarization and PII detection, and use Data Wrangler to clean and shape results, inside Microsoft Fabric.

Learn how AI is transforming Azure Database for PostgreSQL with vector support, indexes, and Visual Studio tools. Discover how to build AI-powered apps in minutes using new features that boost data interaction, understanding, and optimization.

Build a conversational AI agent for Zava, a retail DIY company, that analyzes sales data and helps customers find products. Learn to create secure, intelligent agents using Azure AI Foundry Agent Service, Model Context Protocol (MCP) for external data connections, and PostgreSQL with Row Level Security (RLS) and pgvector for role-based data protection and semantic search.

Any technologist that is looking to apply AI pair-programming techniques with GitHub Copilot to perform challenging work like migrating or translating from one programming language to another. You'll use advanced GitHub Copilot techniques that are specifically useful when translating projects in different programming languages, as well as the different modes GitHub Copilot has to offer.

This lab explores how organizations can leverage their legacy data by unifying their data estate using Microsoft Fabric. Go from data chaos to clarity in this hands-on lab. Learn data ingestion, transformation, and AI-driven insights using Microsoft Fabric and Azure Databricks. Build scalable data solutions and explore agentic AI for smarter decisions and real business impact

Learn how Copilot in Azure boosts app resilience by reviewing logs and streamlining ops. Get hands-on with real scenarios, and see how GitHub Copilot can enhance your build and deployment workflows.