Implementing Agents and Copilots using Semantic Kernel and Azure AI Agent Service

calendar May 1, 2025 - Last Updated: · 3 min read  ·
Share on: linkedin copy

This workshop guides developers through implementing intelligent agents and copilots using Microsoft’s Semantic Kernel and Azure AI frameworks. Participants will explore the Azure AI ecosystem including Azure AI Foundry, Azure OpenAI Service, and the Azure AI Agent Service while mastering agent development fundamentals.

The curriculum progresses from core Semantic Kernel concepts and prompt engineering techniques to advanced implementation of plugins, function calling, and multi-agent solutions.

Participants will learn to leverage Kernel Memory for RAG patterns, integrate with various prompt templates, and orchestrate complex agent behaviors.

Advanced topics include implementing Microsoft 365 Copilot extensions, building agent-to-agent communication systems, and deploying production-ready AI solutions using Azure AI Agent Service with comprehensive content filtering and observability capabilities.

Module 1: Copilot, Agents & Azure AI Foundry Essentials

  • Overview Copilots and Agent Frameworks in the Microsoft Ecosystem
  • Azure AI Foundry: Hubs, Projects and Resources
  • Deploy and use Large Language Models (LLM) in Azure AI Foundry
  • Effective Prompt Engineering
  • Introduction to Azure AI Foundry SDK
  • Integrating your own data using Retrieval Augmented Generation (RAG)
  • Function Calling, Model Context Protocol (MCP) and Agent2Agent (A2A) Protocol Basics
  • Ensuring App Behavior using Evaluations
  • Deploy AI Apps using Azure Developer CLI

Module 2: Develop AI Agents using Azure OpenAI and Semantic Kernel

Semantic Kernel Basics & Concepts

  • Understand the purpose of Semantic Kernel
  • Semantic Kernel Components
  • Chat History & AI Services Integration
  • ChatCompletion and Multi-modal capabilities

Optimizing Prompts

  • Prompt Engineering with Semantic Kernel
  • YAML Prompt Templates and Template Formats
  • Handlebar Prompt Templates
  • Liquid Prompt Templates
  • Using Prompty Visual Studio Code Extension

Implement Plugins for Semantic Kernel

  • Understand the purpose of Semantic Kernel plugins
  • Learn how to use pre-made plugins
  • Planners, Function Calling and Choice Behaviors
  • Implement Native Functions using Prompts
  • Integrate existing API’s using OpenApi Plugins
  • Using MCP Servers in Semantic Kernel
  • Filters & Observability

Kernel Memory & Vector Store Connectors

  • Understand the purpose of Kernel Memory
  • Semantic Kernel Memory: In-process & Out-of-the-box-Connectors
  • Data Model And Embedding Generation
  • Kernel Memory & Retrieval Augmented Generation (RAG)

Semantic Kernel Process Framework

  • Text to Image & Image to Text
  • Using Audio to text
  • Using Hugging Face with Semantic Kernel
  • Integrating Prompt-Flow with Semantic Kernel

Semantic Kernel Agent Framework

  • Agents Overview
  • Completing multi-step tasks with Agents
  • Using Personas with Agents
  • Implementing Multi Agent Solutions

Module 3: Develop Agents using Azure AI Agent Service

  • Introduction to Azure AI Agent Service
  • Using Action Tools: Code Interpreter, Function Calling, Azure Functions and OpenAPI Tools
  • Using Knowledge Tools: File Search, Azure AI Search and Bing Grounding
  • Orchestrating Agents using Semantic Kernel
  • Content Filtering and Observability

Module 4: Implementing Copilots for Microsoft 365

  • Overview of the Microsoft 365 Copilot Ecosystem
  • Implementing Plugins and Connectors for Microsoft 365 Copilot
  • Declarative Agents vs Custom Engine Agents
  • Copilot Agent Plugins for Semantic Kernel (CAPS)