CodeRabbit scales agentic software development and ships 20x more

For Harjot Gill, co-founder and CEO of CodeRabbit⁠(opens in a new window), trusting and validating agentic code is becoming the place where teams bring judgment to a growing volume of AI-generated work. “The first bottleneck that every company hits as soon as you adopt coding agents is code reviews,” Harjot says.

CodeRabbit built an AI-powered governance and control platform designed to validate and trust AI-generated code. Used by over 20,000 organizations and 150,000+ open-source projects, CodeRabbit helps teams understand, review, and secure code produced by AI agents and decide what is ready to ship.

According to CodeRabbit, better price-performance from OpenAI helps it add more AI agents to its reviews and pass the benefits to customers, and Codex⁠ helps it ship 20 times more software with the same engineering team. The company also uses Daybreak⁠ to both secure its own stack and its customers’ code. Its latest offering, CodeRabbit Secure, uses Daybreak with Codex models to find and fix vulnerabilities using its security-focused agents.

“With each OpenAI model release, especially with the reasoning models, we have seen massive improvements in the capabilities of our product to find issues at scale.”

– Harjot Gill, co-founder and CEO, CodeRabbit

Improving code review with OpenAI reasoning models

CodeRabbit built its first product with GPT‑3.5 Turbo. Harjot says the arrival of GPT‑4 made the product effective at reviewing code. The company went on to adopt OpenAI o1 and OpenAI o3 early. Because code reviews run asynchronously in the cloud, CodeRabbit could use models that took longer to reason through a problem in exchange for more capable analysis.

The team evaluates new models against its own benchmark of known issues. At the time of the interview, Harjot estimated that GPT‑6 Astra⁠ caught 50% of the issues in that dataset, putting it at the top compared to other models in that benchmark.