AI coding agents generate more code, but not more software
A study of hundreds of firms finds human code review absorbs the coding gains.
Code#06
49%
Pull request review time after AI agents
Image: Ars Technica
49%Pull request review time after AI agents
The short version
- AI coding agents raised total lines of code generated by 30 percent at firms that adopted them, according to the study.
- Commits rose 20 percent and pull requests rose 23 percent on average.
- Issue resolution rates did not change in a statistically significant way after AI tools were introduced.
- The average review process time from submission to merge rose 49 percent after AI agents were introduced.
Why it matters
The study suggests that faster code generation does not automatically mean more shipped software. For developers, review capacity may be the real limit when AI agents write more code. Teams adopting agents may need to plan for longer reviews.
“little evidence that firms increase software output or reduce employment”