As AI can write so many more lines of code more quickly than humans, the need for code review that keeps pace with development is now an urgent necessity.
A recent survey by SmartBear – whose early founder, Jason Cohen, literally wrote the book on peer code review – found that the average developer can review 400 lines of code in a day, checking to see if the code is meeting requirements and functions as it’s supposed to. Today, AI-powered code review enables reviewers to look at thousands of lines of code.
AI code review provider CodeRabbit today announced it’s bringing its solution to the Visual Studio Code editor, shifting code review left into the IDE. This integration places CodeRabbit directly into the Cursor code editor and Windsurf, the AI coding assistant purchased recently by OpenAI for US$3 billion.
CodeRabbit started with the mission to solve the pain point in developer workflows where a lot of engineering time goes into manual review of code. “There is a manual review of the code, where you have senior engineers and engineering managers who check whether the code is meeting requirements, and whether it’s in line with the organization’s coding standards, best practices, quality and security,” Gur Singh, co-founder of the 2-year-old CodeRabbit, told SD Times.
“And right around the time when GenAI models came out, like GPT 3.5, we thought, let’s use these models to better understand the context of the code changes and provide the human-like review feedback,” Singh continued. “So with the process, we are not necessarily removing the humans from the loop, but augmenting that human review process and thereby reducing the cycle time that goes into the code reviews.”
AI, he pointed out, removes one of the classic bottlenecks in the software development process – peer code review. Also, AI-powered review is not prone to the errors humans make when trying to review code at the pace the organization requires to ship software. And, by bringing CodeRabbit into VS Code, Cursor, and Windsurf, CodeRabbit is embedding AI at the earliest stages of development. “As we are bringing the reviews within the editor, then those code changes could be reviewed before each are pushed to the central repositories as a PR and also before they even get committed, so that developer can trigger the reviews locally at any time,” Singh said.
In the announcement, CodeRabbit wrote: “CodeRabbit is the first solution that makes the AI code review process highly contextual—traversing code repositories in the Git platform, prior pull requests and related Jira/Linear issues, user-reinforced learnings through a chat interface, code graph analysis that understands code dependencies across files, and custom instructions using Abstract Syntax Tree (AST) patterns. In addition to applying learning models to engineering teams’ existing repositories and coding practices, CodeRabbit hydrates the code review process with dynamic data from external sources like LLMs, real-time web queries, and more.”
The post CodeRabbit brings AI-powered code review into Visual Studio Code appeared first on SD Times.
Source: Read MoreÂ
