Designing und Implementing Agents and Pro Code Copilots using Microsoft Agent Framework and Azure AI Agent Service (AZAGENTS)

Module 1: Copilot & Agent Extensibility Fundamentals

Microsoft Foundry Essentials

Copilots & Agent Frameworks in the Microsoft Ecosystem

Deploying LLMs in Microsoft Foundry

Model Router: Smart Model Selection

Microsoft Foundry SDK & Microsoft.Extensions.AI

Infrastructure as Code (IaC) using Azure Developer CLI Agentic Mode\nAgentic AI Fundamentals

What Are Agents & Agentic AI?

Prompt Engineering vs Context Engineering

Knowledge Integration & Agentic RAG

Deep Reasoning & (Reasoning and Acting)

Function Calling, REST APIs & MCP Servers

Evaluating Generative AI Performance

Governance & Guardrails for Responsible Agents\nImplementing Model Context Protocol Servers (MCP)

MCP Core Concepts & Architecture

Transports: STDIO vs HTTP Streaming

Debugging with MCP Inspector

Authentication & Security Best Practices

Hosting MCP’s in Azure Functions

Implementing MCP Apps\nModule 2: Build Agents using Foundry Agent Service

• Introduction to Foundry Agent Service
• Conversations, Runs & State Management
• Knowledge Integration: Foundry IQ, File Search, Azure AI Search, Agent Memory & Bing Grounding
• Executing Actions with Tools: Code Interpreter, Azure Functions, OpenAPI, MCP & Deep Research
• Automating UI Tasks using Browser Automation and Computer Use
• Voice Agent Integration using Azure Speech Voice Live API
• Tracing, Observability & Performance Evaluation
• Hosted Agents: Containerized Deployments with Hosting Adapter & Agent Identity
• Agent-to-Agent Protocol (A2A) & Connected Agents\nModule 3: Orchestrate Agents using Microsoft Agent Framework

Microsoft Agent Framework Basics & Concepts

Introduction to the Agent Framework

Chat Clients vs Agents: Key differences

Agent types and configuration essentials

Integrating Microsoft Foundry agents

Threads, Conversation management & persistence

Implementing long-term memory

Governance, Middleware & Observability

Hosting Agents in ASP.NET Core & Python (AddAIAgent, Responses API)\nAgent Skills & Knowledge

Agent Skills: SKILL.md structure, SkillsProvider & Progressive Disclosure

Code-defined Skills vs. File-based Skills

Agent Skills vs. Workflows: When to use each

Built-in tools: Code Interpreter, File Search, Bing Grounding

Adding custom tools and calling them from agents

Integrating OpenAPI and MCP tools

Function-calling middleware for advanced workflows\nOrchestration, Durable & Hosted Agents

Introduction to Multi-Agent Orchestration

Orchestration Patterns (Sequential, Concurrent, Fan-out/Fan-in)

Durable Agents with Azure Durable Functions (Flex Consumption, auto-scaling)

Conversation State Persistence & Durable Task Scheduler

Hosted Agents: Deploying to Azure Foundry (container images, agent identity)

Branching, Checkpointing & Human-in-the-loop

Observability & Workflow Visualization\nModule 4: Agent Integration using Microsoft Agents SDK

• Overview Microsoft 365 Agents SDK (C#, JavaScript, Python)
• Connecting Copilot Studio & Microsoft Foundry Agents via A2A Protocol
• Orchestrate Multi-Agent Solutions using Microsoft Agent Framework
• Publishing Agentic AI Solutions to Copilot Chat and Teams
• Front-End Integration using Agent–User Interaction (AG-UI) Protocol