Build an application with GitHub Copilot agent mode in less than an hour.
People love how GitHub Copilot helps them write code faster and with fewer errors. But what if GitHub could create a multi-tier application with a presentation, logic, and data layers based on requirements written in natural language? In this exercise, we will prompt GitHub Copilot agent mode to create a complete application.
- Who is this for: Intermediate developers familiar with GitHub Copilot, basic GitHub, and basic web development
- What you'll learn: We'll introduce GitHub Copilot agent mode and how to use it for application development.
- What you'll build: You'll use GitHub Copilot agent mode to create a fitness application as the gym teacher of a high school.
- Prerequisites: Skills Exercise: Getting Started with GitHub Copilot.
- How long: This course takes less than one hour to complete.
In this exercise, you will:
- Start up a preconfigured development environment for making a multi-tier application.
- Prompt in GitHub Copilot Chat and select the edit tab and select agent mode from the edit/agent drop-down.
- Try creating the application with GPT-4o.
- Try other LLM models to see other output.
Simply copy the exercise to your account, then give your favorite Octocat (Mona) about 20 seconds to prepare the first lesson, then refresh the page.
Having trouble? 🤷
When copying the exercise, we recommend the following settings:
-
For owner, choose your personal account or an organization to host the repository.
-
We recommend creating a public repository, since private repositories will use Actions minutes.
If the exercise isn't ready in 20 seconds, please check the "Actions" tab of your repository (or visit https://github.com/<YOUR-USERNAME>/<YOUR-REPO>/actions).
-
Check to see if a job is running. Sometimes it simply takes a bit longer.
-
If the page shows a failed job, please submit an issue. Nice, you found a bug! 🐛
© 2025 GitHub • Code of Conduct • MIT License