AI Assisted Development with GitHub Copilot

Introduction to GitHub Copilot and LLMs

Discover the fundamentals of AI-powered development with GitHub Copilot. Learn how this tool enhances developer workflow through intelligent code suggestions while understanding its capabilities and limitations. Before using the tool, it is crucial to understand the engine behind it. This module explains how Large Language Models work, the difference between static training data and dynamic context, and how GitHub Copilot sits as an orchestration layer on top of these models.

• What is AI pair programming?
• Understanding LLMs
• LLM Static Knowledge vs. Dynamic Knowledge: Training data cut-offs and the Context Window
• GitHub Copilot Licenses
• Setting up Copilot: GitHub Copilot CLI vs Visual Studio (Code)
• Understanding privacy and security considerations
• LAB: Activating GitHub Copilot Free License

Using GitHub Copilot

Master the fundamental interaction modes of GitHub Copilot. In this module, we focus on the out-of-the-box experience, exploring how to interact with the Copilot Chat, how to use built-in tools, and how to streamline your daily coding tasks.

• Code Completions and Next Edit Suggestions
• Copilot Chat: Inline vs. Panel
• Agent Modes: Ask, Edit, Agent and Plan
• Copilot Agent Types
• Git Integration: Commit message generation and PR descriptions
• Understanding GitHub Copilot Tools
• LAB: Refactoring and documenting legacy code using standard chat features

GitHub Copilot Prompt Engineering and Model Selection

Learn how to craft effective prompts and contextual cues to increase Copilot's code generation capabilities. Explore best practices for guiding AI pair programming by giving clear commands dependent on the AI model you are working with.

• What is Prompt Engineering?
• Few-Shot Prompting
• Iterative prompting strategies
• Structuring Prompts with Markdown and XML
• Model Selection: Standard vs Premium Models
• Using your own LLM with GitHub Copilot
• LAB: Guiding Copilot with Prompt Engineering

Extending GitHub Copilot's Tools

First, you'll enhance Copilot's capabilities by learning to integrate custom third-party tools. This integration allows you to query documentation, leverage third-party AI models, and establish communication with external systems. Furthermore, we introduce the Model Context Protocol (MCP), a standard for defining LLM tools and interactions.

• What are GitHub Copilot Tools?
• Universal AI Integrations with the Model Context Protocol (MCP)
• Useful MCP Servers
• Building MCP Servers
• MCP Server Security Considerations
• Providing Copilot with CLI Tools
• LAB: Create a beautiful UI using the Playwright MCP powered Copilot

Customizing GitHub Copilot

While GitHub Copilot acts as a powerful generalist out of the box, its real utility emerges when it is tailored to your specific codebase, coding style, and application architecture. This module demonstrates how to mold the AI to your team's specific needs using a suite of customization features. You will learn how to enforce global standards with Custom Instructions, standardize complex workflows using Prompt Files, and architect Specialized Agents that understand your domain.

• Custom Instructions
• Creating reusable prompts with Prompt Files
• Defining specialized Agents
• Defining reusable capabilities and scripts with Skills
• Automating AI Generated Code Clean-Up with Hooks
• When to use Instructions vs. Prompts vs. Skills vs. Agents?
• LAB: Building custom Instructions, Prompts, Skills and Agents

End-to-End Development with Copilot

Discover how GitHub Copilot transforms every phase of the Software Development Lifecycle (SDLC). Learn to leverage AI assistance from initial requirements analysis through deployment and maintenance, creating a seamless AI-enhanced development workflow that boosts productivity and code quality across your entire project lifecycle.

• GitHub Copilot across the SDLC
• Requirements to Code: Rapid prototyping and API design
• AI-Enhanced Development: Design patterns and optimization
• Automated Testing: Unit tests and edge case generation
• Deployment Support: Configuration and script assistance
• Maintenance Made Easy: Bug fixes and refactoring
• LAB: Building an E-Commerce Platform with Copilot

Expand your Dev Team with GitHub Copilot Cloud Agent

GitHub Copilot Cloud Agent allows you to let GitHub Copilot autonomously implement entire features, starting from high-level requirements. Through an iterative back-and-forth you can steer copilot precisely in the direction you want, without even having to use an IDE! Additionally, Copilot can provide feedback on your developers pull requests with Copilot Code Review, to streamline pull request verification. Additionally using Copilot pull request summaries can speed up code reviews and increase knowledge sharing across the team.

• Introduction to GitHub Copilot Cloud Agent
• Defining Feature Requirements with GitHub Issues
• Assigning Copilot as a Pull Request Reviewer
• Steering Copilot
• Reviewing Changes with GitHub Codespaces
• LAB: Add GitHub Copilot to your Project's Development Team

Building Custom Applications with GitHub Copilot SDK

Take the agentic power of GitHub Copilot beyond the IDE and CLI by embedding it directly into your own applications. This module explores the GitHub Copilot SDK, teaching you how to utilize Copilot's production-tested execution loop to build custom AI workflows, personal productivity tools, and enterprise agents. You will learn to programmatically orchestrate tools, manage multiple AI models, and integrate MCP servers.

• Introduction to the GitHub Copilot SDK
• Understanding the Copilot Agentic Core and Execution Loop
• Setting up the SDK and Authenticating
• Integrating Custom Tools and MCP Servers Programmatically
• Building Custom GUIs and Task-Specific Agents
• LAB: Building a Custom Automation Tool with the Copilot SDK