\nThe “Keynote in 5” video takes a different approach to Build 2025 coverage. Rather than walking through every product announcement, it goes deeper on the technology<\/strong> behind the big ideas \u2014 unpacking how AI agents actually work, what Model Context Protocol really is, and how developers fit into the enterprise AI adoption story.\n<\/p>\n \nThis blog follows that same approach: less product marketing, more technical context. If you want to understand the why<\/em> and how<\/em> behind Microsoft’s Build 2025 announcements, this is the post for you.\n<\/p>\n \nThe term “AI agent” gets used loosely, so let’s be precise. An AI agent is a system that:\n<\/p>\n \nThis is fundamentally different from a chatbot that responds to individual queries. Agents are autonomous executors with access to real-world capabilities.\n<\/p>\n \nMicrosoft’s entire Build 2025 platform is designed to support this pattern at every level \u2014 from individual developers using GitHub Copilot to enterprises running multi-agent workflows in Azure AI Foundry.\n<\/p>\n \nBefore MCP, connecting an AI model to external tools was custom work every time. Want your agent to query a database? Write custom integration code. Want it to search the web? Write another integration. Want it to call your internal API? Yet another integration.\n<\/p>\n \nThis created massive friction and resulted in AI systems that were islands \u2014 powerful but isolated.\n<\/p>\n \nModel Context Protocol<\/strong> defines a standard interface between AI models and the tools\/data sources they need to interact with. Think of it like REST for AI tool use:\n<\/p>\n \nWhen Microsoft says it has deployed MCP support across GitHub, Copilot Studio, Azure AI Foundry, Windows 11, Dynamics 365, and Semantic Kernel, it means any MCP-compatible agent can now talk to all of those platforms without custom integration work.\n<\/p>\n \nBy joining the MCP Steering Committee alongside other major players, Microsoft is ensuring that MCP evolves as a genuinely open standard \u2014 not a standard controlled by any single vendor. This is the right move: open standards create larger, healthier ecosystems than proprietary protocols.\n<\/p>\n \nThe Azure AI Foundry Agent Service (now generally available) is designed for multi-agent orchestration<\/strong> \u2014 the coordination of multiple specialised AI agents working together on a complex task.\n<\/p>\n \nHere’s a concrete example of how this works:\n<\/p>\n \nGoal<\/strong>: “Prepare a quarterly business review presentation”\n<\/p>\n \nEach agent is specialised. The orchestrator (Azure AI Foundry Agent Service) coordinates the workflow, passes outputs between agents, handles errors, and delivers the final result.\n<\/p>\n \nThis is what “agentic AI” looks like in practice \u2014 and it’s now available as a managed Azure service.\n<\/p>\n \nOne of the most technically important announcements was Azure AI Foundry Observability<\/strong>, which provides:\n<\/p>\n \nWithout observability, running agents in production is flying blind. This feature is what separates a demo from a deployable enterprise system.\n<\/p>\n \nUnder the hood, GitHub Copilot’s new autonomous agent capability uses a combination of:\n<\/p>\n \nThe open-sourcing of GitHub Copilot Chat in VS Code means the community can inspect, improve, and extend this pipeline \u2014 a significant step toward collaborative AI development tooling.\n<\/p>\n \nFoundry Local<\/strong> (bringing Azure AI Foundry to Windows 11 and macOS) addresses several real problems:\n<\/p>\n \nModern Windows devices with Qualcomm Snapdragon, Intel Core Ultra, or AMD Ryzen AI chips have dedicated NPU hardware designed for exactly this use case. Windows AI Foundry<\/strong> provides the unified API layer that abstracts the underlying silicon, so developers write once and run on any supported hardware.\n<\/p>\n \nThe “Keynote in 5” video spends time on enterprise AI adoption data, which provides important context:\n<\/p>\n \nThese numbers tell a story: the early adopter phase is over. Enterprise AI with Microsoft’s platform is in mainstream adoption. The challenge has shifted from “will this work?” to “how do we scale it safely?” \u2014 which explains why governance features like Entra Agent ID and Purview SDK were front and centre at Build 2025.\n<\/p>\n \nBased on the technologies highlighted in “Keynote in 5”, here are the most technically valuable areas to invest in:\n<\/p>\n \nBuild MCP servers that expose your organisation’s internal APIs and data sources. Every MCP server you build makes your systems accessible to any MCP-compatible agent \u2014 including GitHub Copilot, Copilot Studio, and any Azure AI Foundry agent.\n<\/p>\n \nStart designing workflows as agent orchestrations rather than monolithic applications. Identify tasks in your codebase or business processes that could be delegated to specialised agents coordinated by Azure AI Foundry Agent Service.\n<\/p>\n \nIf you’re building Windows applications, experiment with Foundry Local for latency-critical or privacy-sensitive use cases. The Phi-4-mini model available via Edge AI APIs is a good starting point for embedded AI features.\n<\/p>\n \nDon’t build agents without observability from day one. Use Azure AI Foundry Observability to instrument every agent action \u2014 cost, latency, quality, and safety. This data is essential for production-readiness.\n<\/p>\n \nThe “Keynote in 5: Unpacking the Tech” video earns its place among the top Build 2025 videos because it doesn’t just tell you what was announced \u2014 it helps you understand the technical foundations beneath the announcements. MCP, multi-agent orchestration, on-device AI, and autonomous coding agents are not marketing terms. They are engineering realities that are available to build with today.\n<\/p>\n \nFor developers who want to stay ahead of the curve, understanding these technologies at a deeper level is the difference between following the trend and leading it.\n<\/p>\n
\nThe Tech Behind the Agentic Web<\/h2>\n
What Is an AI Agent, Really?<\/h3>\n
\n
\nDeep Dive: Model Context Protocol (MCP)<\/h2>\n
The Problem MCP Solves<\/h3>\n
What MCP Does<\/h3>\n
\n
Why the MCP Steering Committee Matters<\/h3>\n
\nDeep Dive: Azure AI Foundry Agent Service<\/h2>\n
Multi-Agent Orchestration<\/h3>\n
\n
Observability: The Missing Piece<\/h3>\n
\n
\nDeep Dive: GitHub Copilot as Autonomous Agent<\/h2>\n
How the Autonomous Coding Agent Works<\/h3>\n
\n
\nDeep Dive: Windows AI Foundry and On-Device AI<\/h2>\n
Why On-Device AI Matters<\/h3>\n
\n
\nDeep Dive: Enterprise AI Adoption \u2014 Where It Actually Is<\/h2>\n
\n
\nWhat Developers Should Build Now<\/h2>\n
1. MCP Server Development<\/h3>\n
2. Multi-Agent Workflow Design<\/h3>\n
3. On-Device AI Applications with Foundry Local<\/h3>\n
4. Observability-First Agent Development<\/h3>\n
\nConclusion<\/h2>\n
\n