AI impact on PR metrics

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.

Automatic AI assistant detection for PRs

To help you understand how AI use affects developer productivity metrics, Swarmia automatically detects pull requests assisted by GitHub Copilot, Cursor, or Claude Code. You can see which AI tools assisted in an individual pull request by opening it anywhere in the app.

A pull request is considered AI-assisted if any of its commits were:

• Made by an author who used an AI tool within the previous 24 hours

• Authored by an AI tool

• Co-authored by an AI tool

You can see the reason for tagging an individual pull request in a tooltip by hovering over the AI tool badge.

Compare pull request metrics by AI coding assistant

The AI impact / Overview / Code page helps you understand 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.

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?

Use the grouping selector to select the data sets you want to compare: maybe AI versus no AI, or different AI coding tools side-by-side.

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.

AI assistant filter

You can filter pull requests in Insights / Cycle time and Insights / Batch size based on the AI tools involved.