AI in Actions

Learn how to integrate AI models directly into your GitHub Actions workflows using GitHub Models.

Welcome

• Who is this for: Developers new to AI integration who want to learn how to incorporate AI capabilities into their GitHub Actions workflows
• What you'll learn: How to use GitHub Models service to add AI inference to your workflows, pass dynamic data to AI prompts, and combine AI actions with other GitHub Actions
• What you'll build: A basic AI question-answering workflow and an automated issue analysis system that comments on new issues
• Prerequisites: Basic familiarity of GitHub Actions (e.g taught in Hello GitHub Actions exercise)
• How long: This exercise takes less than 30 minutes to complete.

In this exercise, you will:

1. Set up a basic AI inference workflow with proper permissions
2. Learn how to combine AI inference with other GitHub Actions to create intelligent automation workflows
3. Build an automated AI issue analysis workflow

How to start this exercise

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.

• 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