Code reviews, which involve peers providing feedback on code, can be quite time-consuming. It’s reported that 50% of companies spend two to five hours per week on these reviews. A lack of people to conduct the reviews can lead to overwhelm and take developers away from important tasks.
Harjot Gill believes that code reviews can be mostly automated through artificial intelligence. As the co-founder and CEO of CodeRabbit, he has developed a platform that utilizes AI models to analyze code and offer feedback.
Before starting CodeRabbit, Gill was the senior director of technology at Nutanix, a datacenter software company. He joined Nutanix when it acquired his startup, Netsil, in March 2018. CodeRabbit’s other founder, Gur Singh, previously led development teams at Alegeus, a white-label healthcare payments platform.
According to Gill, CodeRabbit’s platform utilizes “advanced AI reasoning” to comprehend the purpose behind code and provide “actionable,” “human-like” feedback to developers.
Gill stated, “Traditional static analysis tools and linters are rule-based and often generate high false-positive rates, while peer reviews are time-consuming and subjective. CodeRabbit, by contrast, is an AI-first platform.”
However, there’s anecdotal evidence suggesting that AI-powered code reviews may not be as effective as human-in-the-loop reviews. Greg Foster from Graphite discussed experiments using OpenAI’s GPT-4 for code reviews, which resulted in numerous false positives.
Furthermore, a recent Stanford study found that engineers who use code-generating systems are more likely to introduce security vulnerabilities in their apps. Additionally, copyright concerns persist.
Using AI for code reviews also has logistical drawbacks. Traditional code reviews facilitate knowledge sharing through conversations among developers, an aspect that may be threatened when reviews are outsourced to AI.
Gill maintains a different perspective, stating that CodeRabbit’s AI-first approach improves code quality and significantly reduces the manual effort required in the code review process.
Evidently, CodeRabbit has secured investments and currently serves around 600 organizations, with pilots in progress at “several” Fortune 500 companies.
CodeRabbit recently announced a $16 million Series A funding round led by CRV, with participation from Flex Capital and Engineering Capital. The new funding will be used to expand CodeRabbit’s sales and marketing functions and product offerings, with a focus on enhancing its security vulnerability analysis capabilities.
