The recent additions to the capabilities of GitHub Copilot provide powerful tools to the developer across the entire software development lifecycle (SDLC). This includes working with issues and pull requests on GitHub, interacting with external services, and of course code creation. This lab explores the functionality, providing real-world use cases and tips on how to get the most out of the tools.
Important
Because GitHub Copilot, and generative AI at large, is probabilistic rather than deterministic, the exact code, files changed, etc., may vary. As a result, you may notice slight difference between screenshots and code snippets in the lab and your experience. This is to be expected, and is just the nature of working with this class of tools.
If something appears broken or isn't running correctly, please ask a mentor!
These labs will walk you through the most common workloads with the agent capabilities of GitHub Copilot.
- Setup the environment.
- Configure and interact with external services through Model Context Protocol (MCP).
- Provide context to Copilot through the use of custom instructions, prompt files, and chat participants.
- Complete a site-wide update with the help of Copilot agent mode.
- Assign issues to GitHub Copilot coding agent to allow Copilot to work on tasks asynchronously.
- Create and use custom agents to provide specialized guidance for specific tasks.
- Manage agents to control who has access to your agents and how they're used.
- Iterate on Copilot's work to refine and improve the generated code.
You are a new developer for Tailspin Toys, a fictional company who provides crowdfunding for boardgames with a DevOps theme - a huge market! You are tasked with creating issues to document the desired updates to the application and DevOps flow, then implementing the ability to filter games by both category and publisher. You'll work iteratively, exploring both the site and Copilot's capabilities, to complete the tasks.
OK, let's get going by starting with the setup!