The productivity impact of coding agents

Summary

The study examines how developers use Cursor’s agent and how its adoption affects software productivity across tens of thousands of users. After the agent became the default for eligible organizations, the rate of merged pull requests increased 39% relative to time trends in a baseline group, while revert rates did not change significantly, bugfix rates slightly decreased, and average lines edited and files touched per merged pull request were unchanged. Agent acceptance varied with experience: each standard-deviation increase in years of experience corresponded to an approximately 6% increase in acceptance relative to the mean, and experienced developers were more likely to plan before coding. In a sample of 1,000 users, about 61% of conversation-starting requests concerned implementation, with others focused on explanation or planning. The authors say no single metric yet captures AI’s economic impact on software engineering.

Takeaways

1. 1

   Organizations using Cursor before the agent’s release merged 39% more pull requests after the agent became the default relative to time trends in the baseline group.

2. 2

   For every standard-deviation increase in years of experience, agent-code acceptance increased by approximately 6% relative to the mean.

3. 3

   About 61% of conversation-starting requests in a 1,000-user sample involved implementation; experienced developers were more likely to plan before generating code.