This course explores the use of AI in the context of GitHub Copilot, a generative AI tool for developers. It equips users with the knowledge and skills to use Copilot effectively while mitigating potential ethical and operational risks associated with AI usage.
- AI Developers and Engineers: Professionals involved in creating and deploying AI systems who need to understand the ethical implications and governance frameworks.
- Data Scientists and Analysts: Individuals who work with data and AI models, focusing on ensuring transparency, fairness, and accountability in their work.
- Business Leaders and Managers: Decision-makers who oversee AI projects and need to implement responsible AI practices within their organizations.
- Policy Makers and Regulators: Those responsible for creating policies and regulations around AI usage, ensuring that AI systems are developed and used ethically and safely.
By the end of the course, participants should be able to:
- Apply responsible AI principles and mitigate ethical risks when using GitHub Copilot
- Use GitHub Copilot as an AI pair programmer across IDEs, chat, the command line, and GitHub.com
- Master prompt engineering techniques to transform code comments into precise, actionable code
- Create and configure Copilot Spaces to democratize and ground tribal knowledge
- Leverage advanced Copilot features to build and update applications using Python and JavaScript
- Manage Copilot plans, content exclusions, and contractual protections for secure development
- Streamline the software development life cycle and measure productivity gains
- Generate, plan, and automate unit tests using Copilot tools and agent modes
- Build applications and automate tasks using Copilot Agent Mode and Cloud Agent
- Integrate GitHub MCP Server securely into Visual Studio Code and Copilot Chat
- Enhance code reviews, catch issues early, and optimize pull requests using AI assistance
Module 01: Develop AI agents with Microsoft Foundry and Visual Studio Code
Learn how to build, test, and deploy AI agents using Microsoft Foundry Agent Service through both the Azure portal and Visual Studio Code extension.
Topics
- Understand AI agents and Microsoft Foundry Agent Service
- Explore development approaches
- Build your first agent in Microsoft Foundry
- Set up Visual Studio Code for agent development
- Configure and manage agents in Visual Studio Code
- Extend agent capabilities with tools
- Test, deploy, and integrate agents
- Exercise - Build and deploy an AI agent
Module 02: Integrate custom tools into your agent
Built-in tools are useful, but they may not meet all your needs. In this module, learn how to extend the capabilities of your agent by integrating custom tools for your agent to use.
Topics
- Why use custom tools
- Options for implementing custom tools
- How to integrate custom tools
- Exercise - Build an agent with custom tools
Module 03: Integrate MCP Tools with Azure AI Agents
Enable dynamic tool access for your Azure AI agents. Learn how to connect MCP-hosted tools and integrate them seamlessly into agent workflows.
Topics
- Understand MCP tool discovery
- Integrate agent tools using an MCP server and client
- Use Azure AI agents with MCP servers
- Exercise - Connect MCP tools to Azure AI Agents
Module 04: Build knowledge-enhanced AI agents with Foundry IQ
Learn how to connect AI agents with enterprise knowledge using Foundry IQ. You'll explore how Retrieval Augmented Generation (RAG) solves the knowledge problem for AI agents, discover how Foundry IQ provides a shared knowledge platform that multiple agents can access, improve retrieval quality through data optimization, and configure agent instructions for consistent, cited responses.
Topics
- Understanding RAG for agents
- Explore Foundry IQ
- Configure data sources for knowledge bases
- Configure retrieval with Foundry IQ
- Exercise - Integrate an AI agent with Foundry IQ
Module 05: Integrate your agent with Microsoft 365
Learn how to publish Microsoft Foundry agents to Microsoft Teams and Microsoft 365 Copilot, access workplace data with Work IQ, and test your integrated agents.
Topics
- Understand Foundry agent publishing options
- Publish an agent from Foundry portal to Teams
- Advanced - Use Microsoft 365 Agents Toolkit
- Access Microsoft 365 data with Work IQ
- Test and iterate your integrated agent
- Exercise - Publish a Foundry agent to Teams
Module 06: Build agent-driven workflows using Microsoft Foundry
Workflows enable you to orchestrate AI agents and other components to create intelligent applications. Learn how to build and manage workflows using Microsoft Foundry.
Topics
- Understand Workflows
- Identify Workflow Patterns
- Create workflows in Microsoft Foundry
- Add Agents to a Workflow
- Apply Power Fx in Workflows
- Maintain Workflows in Microsoft Foundry
- Use workflows in code
- Exercise - Create an Agent-driven Workflow
Module 07: Develop an AI agent with Microsoft Agent Framework
This module provides engineers with the skills to begin building Microsoft Foundry Agent Service agents with Microsoft Agent Framework.
Topics
- Understand Microsoft Agent Framework AI agents
- Create an Azure AI agent with Microsoft Agent Framework
- Add tools to Azure AI agent
- Exercise - Develop an Azure AI agent with the Microsoft Agent Framework SDK
Module 08: Orchestrate a multi-agent solution using the Microsoft Agent Framework
Learn how to use the Microsoft Agent Framework SDK to develop your own AI agents that can collaborate for a multi-agent solution.
Topics
- Understand the Microsoft Agent Framework
- Understand agent orchestration
- Use concurrent orchestration
- Use sequential orchestration
- Use group chat orchestration
- Use handoff orchestration
- Use Magentic orchestration
- Exercise - Develop a multi-agent solution
Module 09: Discover Azure AI Agents with A2A
Learn how to implement the A2A protocol to enable agent discovery, direct communication, and coordinated task execution across remote agents.
Topics
- Define an A2A agent
- Implement an agent executor
- Host an A2A server
- Connect to your A2A agent
- Exercise - Connect to remote Azure AI Agents with the A2A protocol
Module 10: Building applications with GitHub Copilot agent mode
Learn how to build applications using GitHub Copilot Agent Mode by prompting autonomous development tasks, using documentation for guidance, and understanding how Agent Mode iteratively manages, refactors, and improves your codebase.
Topics
- What is GitHub Copilot Agent Mode?
- Explore the power of autonomous development assistance
- GitHub skills exercise
Module 11: Accelerate development with GitHub Copilot Cloud Agent
This module explains how to use Copilot Cloud Agent to assign tasks, streamline development, and combine automation with your team's expertise for faster, higher-quality outcomes.
Topics
- Understanding and enabling the GitHub Copilot Cloud Agent
- Security, risks, and limitations of the Copilot Cloud Agent
- Assigning, tracking, and troubleshooting Copilot Cloud Agent tasks
- Customizing, extending, and validating the Copilot Cloud Agent
- Responsible use of GitHub Copilot Cloud Agent on GitHub.com
- Exercise - Expand your team with Copilot Cloud Agent
Module 12: Introduction to MCP Server
This module introduces GitHub MCP Server, a secure and scalable way to integrate GitHub features into your AI tools. You'll learn what MCP is, how to configure GitHub MCP Server in VS Code, use it with Copilot Chat, and troubleshoot common issues.
Topics
- Simplify your AI workflow with GitHub MCP Server
- Configure, connect, and use GitHub MCP Server in VS Code
- Using GitHub MCP Server with Copilot Chat
- Exercise - Integrate MCP with GitHub Copilot
Module 13: Leveling up code reviews and pull requests with GitHub Copilot
This module introduces how GitHub Copilot enhances code reviews by accelerating review cycles, catching issues, and enforcing best practices.
Topics
- What GitHub Copilot adds to the review process
- Using Copilot as a reviewer in GitHub.com
- Catching issues early and automating reviews with Copilot
- Measuring impact and optimizing premium request units (PRUs)
- Exercise - GitHub Copilot code review
Module 14: Using GitHub Copilot with JavaScript
To work with JavaScript, take advantage of GitHub Copilot, an AI pair programmer that boosts productivity with autocomplete-style suggestions.
Topics
- What is GitHub Copilot
- Exercise - Set up GitHub Copilot to work with Visual Studio Code
- Use GitHub Copilot with JavaScript
- Exercise - Update a JavaScript portfolio with GitHub Copilot
Module 15: Using GitHub Copilot with Python
GitHub Copilot is an AI pair programmer that offers autocomplete-style suggestions as you code in Python. AI Disclaimer Previous Versions Blog Contribute
Topics
- What is GitHub Copilot?
- Exercise - Set up GitHub Copilot to work with Visual Studio Code
- Use GitHub Copilot with Python
- Exercise - Update a Python web API with GitHub Copilot
