Study Shows AI Coding Agents Add Code but Lengthen Review Times
Understand the story
A study shows that introducing AI coding agents significantly increases the code review burden in software development: average review time from pull request submission to merge increased by 49%, the share of pull requests requiring changes nearly doubled, comments per pull request increased by 35%, and the share of employees involved in code review rose by 14%. Overall, AI coding agents generate more code but result in less software actually merged, with significantly more time and effort spent on code review.
AI overview of reporting · Updated 9 days ago
Reporting timeline
Explore different aspects of the story through its reporting.
- Ars Technica · AIAI coding agents generate more code, but not more software
A study found that after AI coding agents were introduced, pull request review time from submission to merge rose 49% on average, the share of pull requests requiring changes nearly doubled, comments per pull request rose 35%, and the share of employees participating in code review increased 14%.
Story heat trend
Current heat3·Comparable peak3（10/11 18:00）·Comparable change over 24 hours –
The trend compares the same continuously observed sources, which may cover fewer sources than the current heat score. Hover or select the chart to inspect each hour; use the left and right arrow keys to navigate.