Back Issues/Search Home → Calendar → Archive → RSS → Subscribe → Services → Vendors → Blog → Current Issue → Popular → Newsletters (LinkedIn, Substack)

All issues › Volume 344, Issue 2 › IT Vendor News › OpenAI

CodeRabbit Scales Agentic Software Development and Ships 20x More

OpenAI, Monday, November 9th, 2026

CodeRabbit uses OpenAI models to review and secure AI-generated code, and Codex to ship 20 times more software with the same team.

CodeRabbit runs an AI governance and code review platform used by more than 20,000 organizations and 150,000 open source projects to validate code written by AI agents, and CEO Harjot Gill says code review is the first bottleneck companies hit when they adopt coding agents.

CodeRabbit tests new models against its own benchmark of known issues, where GPT-6 Astra caught 50 percent, the top score.

Lower pricing and caching let it run many more subagents on models such as GPT-6 Luna, with GPT-6 Astra handling planning.

The company says Codex helps it ship 20 times more software, and its new CodeRabbit Secure uses Daybreak to find and fix vulnerabilities.

more →  ·  More from OpenAI →