Compare pull request metrics by AI coding assistant

You can now see how pull requests assisted by different AI coding tools — or no AI tools — perform across metrics like throughput, cycle time, batch size, and review time. You’ll find this and all the AI adoption, activity, and impact views under the new AI impact section in the main navigation.

When you connect GitHub Copilot, Cursor, or Claude Code to Swarmia, we automatically tag pull requests as AI-assisted if any of their commits were made by an AI tool or by someone who was active on an AI tool. The new comparison view, available at AI impact → Impact, brings all this data together in one place, so you can see patterns without jumping between tabs.

Use the aggregate selector to view averages, or choose from various percentiles to reduce the effect of outlier pull requests. You can also apply filters like repository to understand where AI-assisted work differs from other work.

This makes it easier to answer questions like: Is AI-assisted work moving through your system faster or slower? Which teams benefit most from AI tools? How are quality indicators responding to increased AI usage?

To get started, connect your AI coding assistants in settings → AI assistants.