A study of 718 firms found that coding agents increased lines of code by 30% but did not yield a statistically significant increase in completed work. The additional code appears to have been absorbed by the review process, leading to a 49% rise in review time and a near doubling of pull requests requiring changes. This suggests an organizational bottleneck in code review capacity, rather than a lack of developer output, is limiting overall productivity gains.
Read the full article at DEV Community
Want to create content about this topic? Use Nemati AI tools to generate articles, social posts, and more.



