Track AI-assisted pull requests

Understanding AI’s impact on your team’s work can be tricky. For example, if AI helps developers write code faster, they might create larger pull requests, which could actually slow down the review process.

Swarmia now automatically detects pull requests assisted by GitHub Copilot, Cursor, or Claude Code. This helps you understand how using AI affects developer productivity metrics, such as pull request cycle time, throughput, and batch size.

A pull request is considered AI-assisted if any of its commits were made by an AI tool or a human who was active on an AI tool. You can see which AI tools assisted in an individual pull request by opening it anywhere in the app. To see the effect on metrics, you can filter pull requests in cycle time and batch size insights based on the AI tools involved.

To get started, connect GitHub Copilot, Cursor, and/or Claude Code to Swarmia in settings → AI assistants.

More updates

With our latest updates, you can:

• See Jira/Linear issue type in issue details popup. This gives you additional context when you use more granular issue types in your issue tracker.
• Highlight an author in the work log. This makes it easier to see every team member’s contribution.
• Toggle to exclude uncategorized from investment balance. This makes it easier to analyze breakdowns that don’t categorize all work.