Udemy
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
GitHub Copilot - The Complete Guide 2026: Agents, CLI & MCP
Rating: 4.6 out of 5(22,043 ratings)
87,040 students

GitHub Copilot - The Complete Guide 2026: Agents, CLI & MCP

Master agentic coding, MCP, Agent Mode & Copilot CLI. Prepare for the GH-300 GitHub Copilot Certification
Created byAlex Dan
Last updated 11/2026
English
Bulgarian [Auto],Czech [Auto],

What you'll learn

  • Use GitHub Copilot in Visual Studio Code: chat, inline suggestions, and the agent, ask and plan modes
  • Build custom agents and agent skills for GitHub Copilot, and know when to use each one
  • Connect GitHub Copilot to GitHub, databases and other tools with MCP (Model Context Protocol) servers
  • Assign issues to the GitHub Copilot cloud agent and use Copilot code review on pull requests
  • Work from the terminal with GitHub Copilot CLI: sessions, models and MCP servers
  • Build a project with Copilot in JavaScript/TypeScript, Python, Java or .NET (C#): API endpoints, a database and tests
  • Understand the GH-300 GitHub Copilot certification exam, including Responsible AI and Copilot plans
  • Set project rules for Copilot with custom instruction files, AGENTS md and agent hooks
  • Give Copilot the right context, pick the right model and use prompt engineering to get reliable results
  • Generate GitHub Actions workflows, debug failing CI tests, run tests in Docker and write Terraform with Copilot
  • Use your own API key (BYOK) or free local models with Ollama inside GitHub Copilot
  • Keep token usage and costs down under Copilot's usage-based billing

Course content

15 sections • 83 lectures • 4h 45m total length
  • GitHub Copilot overview — what we'll cover3:33

    How the sections build on each other, from Copilot Chat basics to agents, a hands-on project and the GH-300 exam, and which optional lectures you can skip.

  • First tip0:17
  • The Udemy experience2:09

    Where to find each lecture's resources, how to ask a good question in the Q&A section, and Udemy features that make technical videos easier to follow.

  • What Is GitHub Copilot?3:51

    Copilot's main features, from code completion and chat to agent mode and the cloud agent, and how it combines your prompt with project context before sending it to a large language model.

  • Setting Up GitHub Copilot in VS Code3:13

    Sign in to GitHub Copilot in VS Code with your GitHub account, choose a plan and confirm that the chat responds, with a quick look at the JetBrains plugin.

  • Optional: Copilot Privacy Settings2:19

    GitHub Copilot privacy settings covering data usage for AI model training on Free, Pro, and Pro+ plans, and how to opt out through the Copilot account settings.

  • Optional: Troubleshooting Copilot3:10

    What to check when Copilot stops responding: the Output logs, the Reload Window command, Chat Diagnostics for service status and your Copilot settings on GitHub.

  • Introduction to GitHub Copilot - Quiz

Requirements

  • Basic programming experience in any language. The hands-on project is available in JavaScript/TypeScript, Python, Java and .NET (C#)
  • Visual Studio Code. The course is recorded in VS Code; if you use a JetBrains IDE such as IntelliJ IDEA, the setup lecture shows where to install the Copilot plugin
  • A GitHub account with GitHub Copilot. The Free plan is enough to try things out; a paid plan is recommended for the agentic sections
  • Basic Git and GitHub knowledge (commits, branches, pull requests, issues) for the cloud agent and GitHub Actions sections
  • Optional: a database you can install locally (MySQL, PostgreSQL or MongoDB) and Docker, to follow the database and CI lectures hands-on

Description

Updated November 2026: the whole course is re-recorded for the current GitHub Copilot in Visual Studio Code. It adds new sections on the cloud agent, CI/CD with GitHub Actions and the GH-300 certification, and a hands-on project you can follow in JavaScript/TypeScript, Python, Java or .NET.

GitHub Copilot is no longer just code completion. In agent mode it plans a task, edits several files, runs commands, calls tools through MCP servers and can open a pull request on its own. This course shows you how to use these features on real code, how to customize them for your project, and how to stay in control of what the agent does.

What you will learn

Copilot in VS Code

  • Copilot Chat with the agent, ask and plan modes, inline chat and inline code suggestions

  • Choosing a model and thinking effort, giving Copilot the right context, slash commands and # tools

  • Prompt engineering tips, and what Copilot really sends to the model (Chat Debug view)

  • Sharing your running web app with Copilot through the VS Code integrated browser

Customizing Copilot

  • Custom instruction files (copilot-instructions md and targeted .instructions md files) and AGENTS md

  • Sharing customizations through the .github folder, or using them in every project from your user .copilot folder

  • Commit message instructions and agent hooks

Agentic AI with Copilot

  • Custom agents with their own model, tools and instructions

  • Agent skills: SKILL md files with scripts that Copilot loads only when the task needs them

  • MCP (Model Context Protocol) servers: the GitHub MCP server and servers you configure yourself in mcp.json

  • When to use instructions, skills, custom agents or MCP, the Awesome Copilot collection, and saving tokens under usage-based billing

Hands-on project A small online pizza shop with a website and a REST API. The backend comes in JavaScript/TypeScript, Python, Java and .NET (C#), so you can follow along in the language you use at work. With Copilot you will:

  • explore the codebase;

  • add instruction files and new API endpoints;

  • connect a MySQL database using plan mode (PostgreSQL or MongoDB work too);

  • review the code with a second model;

  • query the data through an MCP server;

  • turn a conversation into a skill;

  • generate unit and integration tests.

Copilot on GitHub and in CI/CD

  • The GitHub Copilot cloud agent (coding agent): start sessions, assign GitHub issues and review the pull requests it opens

  • Copilot code review on your own pull requests

  • GitHub Actions: generate a workflow, debug failing Playwright tests from the CI logs, run the tests in Docker and generate Terraform for AWS

Models and the terminal

  • Bring your own key (BYOK), for example Claude models with an Anthropic API key

  • Free, private local models with Ollama inside Copilot

  • GitHub Copilot CLI: installation, sessions, models and MCP

GH-300 certification guide A section about the GH-300 GitHub Copilot certification exam: Responsible AI, Copilot plans and enterprise features, and an overview of the exam. The course doesn't include practice tests. What it gives you for the exam is hands-on experience with the Copilot features the exam asks about.

How the course is made

  • Fast paced: the typing is cut out and the focus stays on explanations

  • Big font and dark theme in full HD, readable even on a tablet

  • A quiz at the end of each section

  • The prompts and the project code as downloadable resources

  • I answer your questions in the Q&A

Course updates

  • November 2026: the whole course re-recorded. New: a hands-on project with four backend languages, the cloud agent and Copilot code review, CI/CD with GitHub Actions, and a GH-300 certification guide.

  • June 2026: new chat interface, agentic AI, Chat Debug view, prompt files, hooks, skills, custom agents, external and local models.

Who this course is for:

  • Developers who use GitHub Copilot for autocomplete and chat and want to move to agent mode, custom agents, skills and MCP
  • JavaScript/TypeScript, Python, Java and .NET (C#) developers. The hands-on project is available in all four languages
  • Teams adopting the GitHub Copilot cloud agent, Copilot code review and Copilot CLI
  • DevOps and QA engineers who want Copilot to generate tests, GitHub Actions workflows, Docker setups and Terraform files
  • Developers preparing for the GH-300 GitHub Copilot certification who want hands-on experience with the features the exam covers
  • Developers who want to run Copilot with their own API keys or local models for privacy or cost reasons