O'Reilly Archive: Hands-On Microsoft Foundry

Level: Intermediate. Theme: Build, scale, and operationalize AI agents in Azure.

As generative AI and autonomous agents continue to transform enterprise workflows, organizations are increasingly turning to Microsoft Foundry, Microsoft’s unified, model agnostic AI platform, to design, build, and scale secure orchestrated agent based applications. The course demonstrates the practical tools and end to end workflows needed to plan, develop, and operationalize intelligent AI agents that can reason, remember, and take autonomous action, while integrating into existing enterprise ecosystems.

Through interactive design principles and over 90 minutes of hands-on development demos, you’ll build intelligent agents from the ground up: defining agent behaviors, connecting external and internal tools, managing persistent memory, and simulating task completion scenarios. You’ll get a deep working knowledge of Microsoft Foundry’s architecture and the Model Context Protocol (MCP) for structured tool and API integration. The course also covers best practices for debugging, refining, and scaling agent applications, using multi-agent workflows, trace inspection techniques, and enterprise ready deployment pipelines.

What you’ll learn

• Understand the architecture, capabilities, and agent lifecycle in Microsoft Foundry
• Learn how the Model Context Protocol (MCP) enables structured orchestration and tool invocation
• Use tools, memory, and goals to create intelligent agents
• Apply best practices for deploying and monitoring agents in enterprise environments
• Build and simulate goal based agents using Microsoft Foundry Studio
• Integrate MCP wrapped tools and external APIs securely
• Design multi-agent workflows that collaborate across tasks
• Evaluate and deploy agents using trace inspection and telemetry

This course is for you if

• You’re an architect, developer, or AI subject matter expert building intelligent applications
• You want to operationalize AI agents on a secure, governed Azure platform
• You’re exploring how to scale beyond copilots into task oriented agents

Prerequisites

• Optional: a free Microsoft account and either a Microsoft Azure 30 day trial or a paid Azure subscription to follow along with demonstrations
• Familiarity with cloud based AI services and LLMs
• Basic experience with REST APIs and Azure services
• Development experience in Python or C#

Schedule

Introduction to agent development in Microsoft Foundry (55 minutes). Core concepts: goals, memory, tools, and orchestrator. Overview of Microsoft Foundry and Agent Service. Agent lifecycle. How agents differ from chatbots or copilots. Demo: spinning up a basic goal based agent in Microsoft Foundry Studio, simulating interaction, and inspecting the goal trace. Group discussion and Q&A.

Building and operationalizing an agent (55 minutes). Authoring goals and planner configurations. Configuring memory. Deploying agents and exposing them via REST APIs. Using simulation output and logs. Demo: building and testing a memory enabled agent and evaluating behavior in the simulation panel. Q&A.

Integrating MCP tools and APIs with your agent (55 minutes). What is the Model Context Protocol. Roles of the MCP server and client. Wrapping async tools as OpenAPI compatible functions. Registering and invoking tools securely. Governance and authentication. Demo: registering an MCP wrapped API tool, simulating tool invocation, and reviewing the trace. Group discussion and Q&A.

Designing and deploying multi-agent solutions (55 minutes). Designing for modular workflows. Defining agent roles (planner versus tool agents). Conversation state and chaining. Multi-agent topologies and deployment.