Building AI Applications
summary
Claim: Microsoft Foundry and its Agent Framework run production agents now — teams deploy models, orchestrate multi‑agent flows and observe + govern them. Demos use Microsoft Foundry, the Azure MCP server (GA covering 47 services), OpenAI/Anthropic models, VS Code + GitHub Copilot, and the Agent Framework; numbers called out include ~11,000 models, ~80,000 Foundry orgs and >1M agents (25k orgs using Autogen/SK). The workshop builds a pizza‑ordering agent (vector store for menus, function‑calling + an MCP pizza server), and it actually places orders end‑to‑end.
AI-written summary · about
chapters (11)
- 0:00Start
- 10:44Opening Keynote: Microsoft CoreAI’s Executive Vice President Jay Parikh and Principal Community Team PM Lead James Montemagno kick off the event with insights into the future of AI development.
- 27:39Build and Manage AI Apps with Your Agent Factory, Yina Arenas, Amanda Silver, Sarah Bird, Marco Casalaina – Step into the era of modular AI. Join our engineering leaders to see how Microsoft Foundry lets you build, orchestrate, and manage intelligent agents using new workflow capabilities. Learn how to unify models, data, and tools with enterprise-grade security and observability.
- 50:43AI powered automation & multi-agent orchestration in Microsoft Foundry, Shawn Henry – Build multi-agent systems the right way with Microsoft Foundry. Go from single-agent prototypes to fleet-level orchestration using the Microsoft Foundry Agent Framework (Semantic Kernel + AutoGen), shared state, Human in the loop, OpenTel, MCP toolchains, A2A, and the Activity Protocol. Bring frameworks like LangGraph and OpenAI Agents SDK, then deploy as containerized, governed, observable agents on Microsoft Foundry.
- 1:21:38Unlock agentic workflows for your apps using MCP on Windows, Alexander Sklar, Roberth Karman – Learn how Windows enables agentic workflows via MCP, connecting native apps, tools, and AI agents. This session covers MCP server development—packaging, security, and MCP Registry integration—and how agents use built-in/custom MCP servers to automate tasks across Windows. Discover how MCP delivers secure, scalable, and extensible AI experiences for users and enterprises.
- 1:51:05Aspire for AI Applications, David Fowler, Damian Edwards – Orchestrate front ends, APIs, containers, and databases effortlessly—no rewrites, no limits. Extend Aspire to power any project. When building AI applications developers need insights into their apps flow, token usage, and more. Join David & Damian as they show off the latest Aspire features that streamline AI app development.
- 2:22:32Ship faster. Stress less. Idea to Ops with Azure and GitHub Copilot, Nir Mashkowski, Mandy Whaley – Explore how GitHub Copilot and intelligent agents streamline Azure application development from design to operations. This session covers how the Coding Agent, App Modernization agent, and cloud architecture agent accelerate planning and coding, while GitHub Copilot for Azure and the Azure MCP Server simplify deployment and diagnostics. Learn how the SRE Agent and testing agent extend automation into production and quality assurance, enabling end-to-end DevOps with AI-powered workflows.
- 2:50:53Driving agentic innovation with MCP as the backbone of tool-aware AI, Maria Naggaga – In this technical deep-dive, Maria unveils how Microsoft is shaping the future of agent-tool interactions through the Model Context Protocol (MCP). As AI agents evolve from simple task runners to autonomous collaborators, MCP emerges as the preferred communication mechanism—enabling secure, scalable, and OS-agnostic tool orchestration across platforms like Microsoft Foundry, GitHub, and VS Code
- 3:12:52Building AI Agents with VS Code and GitHub, April Gittens, Rong Lu – In this interactive session, you’ll build and deploy an AI agent using the latest AI Toolkit and GitHub Copilot features inside VS Code. You’ll start with a prototype setup, where Copilot connects to the AI Toolkit through an MCP server to suggest models, open the model playground, instrument code for tracing, enable viewing traces, and finally deploy the agent to Azure. You’ll leave with a functioning, traced, and deployed agent — plus a repeatable local-to-cloud workflow.
- 3:37:56From prompt to production: Build real-world AI apps with Microsoft Foundry using models from OpenAI/Anthropic, Scott Addie, Arun Sekhar – Unlock the power of Microsoft Foundry Models to deliver enterprise-ready AI solutions. In this session, you’ll learn how to integrate OpenAI and Anthropic models into your apps using Microsoft’s AI ecosystem. Whether you’re modernizing workflows or creating intelligent experiences, this session equips you with practical guidance and demos to accelerate your AI journey.
- 4:07:30Day 1: Live Hands-On Workshop
related talks
36mBuilding AI Agents in .NET with Azure AI Foundry
07h 25mAI Agents Conference 2026 - Day 2
56mBuilding AI Agents and Multi-Agent Systems with Azure AI
20mGenAI agents - Evolution of automation
58mAdvanced Autonomous AI Agents: Memory, Collaboration and Evolution in Action
39mEvolving Intelligence: Designing Autonomous AI Agents
34mArchitecting AI Agents with Microsoft Agent Framework
01h 54mBuilding Code First AI Agents with Azure AI Agent Service