Does AI Code Review Lead to Code Changes? A Case Study of GitHub Actions
For developers and tool designers, this work provides empirical evidence on which factors make AI code review comments actionable, though the findings are incremental as they confirm known usability principles.
This study analyzes 22,000+ review comments from 16 AI-based code review tools across 178 GitHub repositories, finding that effectiveness varies widely and that concise comments with code snippets from manually triggered hunk-level tools are most likely to lead to code changes.
AI-based code review tools automatically review and comment on pull requests to improve code quality. Despite their growing presence, little is known about their actual impact. We present a large-scale empirical study of 16 popular AI-based code review actions for GitHub workflows, analyzing more than 22,000 review comments in 178 repositories. We investigate (1) how these tools are adopted and configured, (2) whether their comments lead to code changes, and (3) which factors influence their effectiveness. We develop a two-stage LLM-assisted framework to determine whether review comments are addressed, and use interpretable machine learning to identify influencing factors. Our findings show that, while adoption is growing, effectiveness varies widely. Comments that are concise, contain code snippets, and are manually triggered, particularly those from hunk-level review tools, are more likely to result in code changes. These results highlight the importance of careful tool design and suggest directions for improving AI-based code review systems.