Setting up Copilot Extensions

1. Learn about Agents Copilot

Agents Copilot contain the custom code for your Extension Copilot, and integrate with a GitHub App to form the Extension Copilot itself. For more information, see About agents for Copilot Extensions.

To successfully build a Agent Copilot, you need to understand how the agent communicates with:

• The Copilot platform using server-sent events. See Configuring your Copilot agent to communicate with the Copilot platform.
• The GitHub API. See Configuring your Copilot agent to communicate with GitHub.

2. Review example Agents Copilot and the Extensions Copilot SDK

To see the previous concepts in practice and learn about agent implementations, review the following example agents and software development kit (SDK), all of which are available in the copilot-extensions organization:

• Blackbeard (best starting point): A simple agent that responds to requests like a pirate using Copilot's large language model (LLM) API and special system prompts.
• GitHub Models: A more complex agent that lets you ask about and interact with various LLMs listed on the GitHub Marketplace through Copilot Chat. The GitHub Models agent makes use of function calling.
• Function Calling: An example agent written in Go that demonstrates function calling and confirmation dialogs.
• RAG Extension: An example agent written in Go that demonstrates a simple implementation of retrieval augmented generation.
• Preview SDK: An SDK that streamlines the development of Extensions Copilot by handling request verification, payload parsing, and response formatting automatically. This SDK allows extension builders to focus more on creating core functionality and less on boilerplate code.

3. Build a Agent Copilot

Using the reference material from the previous steps, plan and build your Agent Copilot. You can choose to implement any of the following options:

• To avoid building and managing your own LLM deployment, your agent can call the Copilot LLM deployment. See Using Copilot's LLM for your agent.
• To quickly interpret user input and choose from a variety of predefined functions to execute, you can implement function calling in your agent. To learn more, see How to use function calling with Azure OpenAI Service in the Azure OpenAI documentation and Function calling in the OpenAI documentation.

4. Deploy your Agent Copilot

To make your Agent Copilot accessible to the Copilot platform and GitHub, you need to deploy it to a server that is reachable by HTTP request. See Configuring your server to host your Copilot extension.

5. Create a GitHub App and integrate it with your Agent Copilot

To create a Extension Copilot, you need to create and configure a GitHub App, then integrate it with your Agent Copilot. See Creating a GitHub App for your Copilot Extension and Configuring your GitHub App for your Copilot extension.

6. Choose the availability of your Extension Copilot

Choose one of two visibility levels for your Extension Copilot:

• Public: Any user or organization account with the installation page link for the extension can install it.
• Private: Only the user or organization account that created the extension can install it.

If you make your Extension Copilot public, you can then choose to list it on the GitHub Marketplace.

To learn how to change the visibility of your Extension Copilot and list it on the GitHub Marketplace, see Managing the availability of your Copilot Extension.

Next steps

To learn how to use your Extension Copilot, see Utilisation d’extensions pour intégrer des outils externes à Copilot Chat.