Automated Code Review In Practice
Umut Cihan, Vahid Haratian, Arda İçöz, Mert Kaan Gül, Ömercan Devran, Emircan Furkan Bayendur, Baykal Mehmet Uçar, Eray Tüzün
TL;DR
Automated code review tools powered by large language models promise to reduce manual review effort and improve quality, but evidence from real industry deployments is scarce. Using an evaluative case study at Beko with CodeReviewBot built on Codium/Qodo and GPT-4, the study analyzes 4335 PRs, of which 1568 received automated reviews. Key findings include that 73.8% of automated comments were resolved, PR closure times increased on average, and human review activity did not consistently decline, while developers perceived modest quality benefits with caveats. These results inform practitioners about potential benefits and pitfalls of adopting automated reviews and motivate further cross company research on human AI interaction in code review.
Abstract
Code review is a widespread practice to improve software quality and transfer knowledge. It is often seen as time-consuming due to the need for manual effort and potential delays. Several AI-assisted tools, such as Qodo, GitHub Copilot, and Coderabbit, provide automated reviews using large language models (LLMs). The effects of such tools in the industry are yet to be examined. This study examines the impact of LLM-based automated code review tools in an industrial setting. The study was conducted within a software development environment that adopted an AI-assisted review tool (based on open-source Qodo PR Agent). Around 238 practitioners across ten projects had access to the tool. We focused on three projects with 4,335 pull requests, 1,568 of which underwent automated reviews. Data collection comprised three sources: (1) a quantitative analysis of pull request data, including comment labels indicating whether developers acted on the automated comments, (2) surveys sent to developers regarding their experience with reviews on individual pull requests, and (3) a broader survey of 22 practitioners capturing their general opinions on automated reviews. 73.8% of automated comments were resolved. However, the average pull request closure duration increased from five hours 52 minutes to eight hours 20 minutes, with varying trends across projects. Most practitioners reported a minor improvement in code quality due to automated reviews. The LLM-based tool proved useful in software development, enhancing bug detection, increasing awareness of code quality, and promoting best practices. However, it also led to longer pull request closure times and introduced drawbacks like faulty reviews, unnecessary corrections, and irrelevant comments.