Agentic Coding with GitHub Copilot training course

The Shifting Role of the Developer

• From code writer to analyst, agent architect, and reviewer
• What is agentic coding?
• The agentic loop: reason, use tools, observe, iterate
• Agentic coding tool landscape: GitHub Copilot, Claude Code, OpenAI Codex, and Cursor

Introduction to GitHub Copilot and LLMs

• Understanding Large Language Models and static vs. dynamic knowledge
• GitHub Copilot licenses
• GitHub Copilot CLI vs. Visual Studio (Code)
• Model selection: choosing the best model for the job
• Privacy and security considerations
• Lab: Activating GitHub Copilot Free License

Fundamentals of GitHub Copilot

• Code completions and Next Edit Suggestions
• Copilot Chat: inline vs. panel
• Agent modes: Ask, Edit, Agent, and Plan
• Copilot agent types
• Commit message generation and PR descriptions
• Understanding GitHub Copilot tools
• Lab: Refactoring and documenting legacy code using standard chat features

AI Across the SDLC: Analysis and Design

• Extracting and clarifying requirements with AI
• Prompt engineering specs
• API and architecture design with Copilot
• Architecture Decision Records (ADRs) as steering context
• Managing issues and work items
• Lab: Designing the e-commerce platform — specs, API, and architecture

Integrations with MCP and CLI Tools

• Universal AI integrations with the Model Context Protocol (MCP)
• Useful MCP servers
• MCP server security considerations
• Context efficiency: MCP vs. CLI tools
• Providing Copilot with CLI tools
• Lab: Create a modern UI using Copilot and the Playwright CLI

Skills, Agents and Hooks

• Custom Instructions
• Defining specialized agents
• Defining reusable capabilities and scripts with Skills
• Automating AI-generated code clean-up with Hooks
• When to use Instructions vs. Skills vs. Agents
• Lab: Building custom Instructions, Skills, and Agents

Expand Your Dev Team with GitHub Copilot Cloud Agent

• Introduction to Cloud Agent
• Defining feature requirements with GitHub Issues
• Assigning Copilot as a pull request reviewer
• Steering Copilot
• Reviewing changes with GitHub Codespaces
• GitHub Agentic Workflows: defining autonomous AI workflows
• Triggering agentic workflows from issues, comments, and schedules
• Lab: Add GitHub Copilot to your project's development team

AI Across the SDLC: Implementation and Testing

• Using test suites as guardrails for the agent
• The test-driven development loop with Copilot
• Static analysis, linters, and analyzers as feedback signals
• Hooks for deterministic agent steering
• End-to-end UI verification with the Playwright CLI
• Lab: Building and testing the e-commerce platform with Copilot

AI Across the SDLC: Reviewing and Verifying AI-Generated Code

• Reviewing large AI-produced diffs efficiently
• Static analysis and security scanning as objective review signals
• Verifying behaviour with tests, Playwright, and benchmarking tools
• Steering the agent to produce reviewable, incremental changes
• Lab: Reviewing, verifying, and hardening the e-commerce platform

Building Custom Applications with GitHub Copilot SDK

• Introduction to the GitHub Copilot SDK
• 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