AI-Assisted Assessment of Coding Practices in Modern Code Review Article Swipe
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.1145/3664646.3665664
· OA: W4398795735
Modern code review is a process in which an incremental code contribution\nmade by a code author is reviewed by one or more peers before it is committed\nto the version control system. An important element of modern code review is\nverifying that code contributions adhere to best practices. While some of these\nbest practices can be automatically verified, verifying others is commonly left\nto human reviewers. This paper reports on the development, deployment, and\nevaluation of AutoCommenter, a system backed by a large language model that\nautomatically learns and enforces coding best practices. We implemented\nAutoCommenter for four programming languages (C++, Java, Python, and Go) and\nevaluated its performance and adoption in a large industrial setting. Our\nevaluation shows that an end-to-end system for learning and enforcing coding\nbest practices is feasible and has a positive impact on the developer workflow.\nAdditionally, this paper reports on the challenges associated with deploying\nsuch a system to tens of thousands of developers and the corresponding lessons\nlearned.\n
