GitHub Copilot activity breakdown

See detailed GitHub Copilot activity patterns across teams, editors, and programming languages

Available at AI impact / Activity / GitHub Copilot

If you're looking for a productivity boost from GitHub Copilot, it's not enough to enable the tool for your teams and then forget it. People need to pick up the new habit and invest the time to learn how to use it effectively. To support that, you need proper visibility into the current activity patterns.

With GitHub Copilot activity breakdown, you can:

• Understand where Copilot is gaining traction and where extra support may be needed.

• Know if people are just trying it out or actively relying on it in their work.

• Notice patterns in how suggestions are used across editors and programming languages.

GitHub reports Copilot usage only:

1. for teams with at least 5 users with an active license

2. based on the direct members of the GitHub team, not the child teams' members

Read more in our full guide:

Measure the productivity impact of AI tools

To track GitHub Copilot adoption and licenses, see:

AI adoption metrics

Setup

Enabling GitHub Copilot metrics:

AI coding tool integrations

Definitions

• Active users = Users who received a suggestion (even if they didn't accept it) in their IDE or chatted with Copilot on a given day. Users must have telemetry enabled in their IDE for their activity to be included. Read more

• Engaged users = Users who engaged with Copilot (accepted a code suggestion, prompted Copilot chat, triggered a PR Summary, etc) on a given day.

• Code suggestions = The number of Copilot code suggestions (from IDE code completions)

• Code acceptances = The number of Copilot code suggestions (from IDE code completions) accepted by users

• Acceptance rate (suggestions) = Code acceptances / Code suggestions

• Lines suggested = The number of lines of code suggested by Copilot (via IDE code completions)

• Lines accepted = The number of lines of code suggested by Copilot (via IDE code completions) and accepted by users

• Acceptance rate (lines) = Lines suggested / Lines accepted

Not all accepted code ends up in the codebase. An engineer could accept 200 Copilot-generated lines over the course of creating a 10-line pull request.

You can't use these metrics to get an accurate number of the share of your code that's AI-generated.

Frequently asked questions

Why does the team selector have different teams than the ones I have configured in Swarmia?

GitHub reports Copilot usage only based on the GitHub teams in your organization. You can configure the team memberships in GitHub. We recommend setting up your Swarmia teams based on your GitHub teams, so that they're a one-to-one match.

Why is some/all of the data missing for the selected team?

Possible reasons:

1. Copilot Metrics API must be enabled in your organization for us to get the usage data. Check your organization's settings. It can take up to 6 hours for Swarmia to sync the data after you've enabled the API.

2. GitHub reports Copilot usage only for days when the team had at least 5 users with an active license. Try selecting a larger team or another timeframe.

3. GitHub reports Copilot usage only based on the direct members of the GitHub team, not the child teams' members.

Do these metrics include the Copilot coding agent and Copilot agent mode?

• Copilot coding agent works autonomously in GitHub Actions to complete tasks assigned through GitHub issues or GitHub Copilot Chat prompts, and creates pull requests with the results.

• Copilot agent mode allows Copilot to make autonomous edits directly in your local development environment (as a part of the Copilot Edits feature in Visual Studio and Visual Studio Code).

No, currently, the GitHub Copilot activity breakdown in Swarmia includes only IDE code completions, but data from more modes will be added soon.