CodeRabbit says Codex helped it ship 20 times more software
Original title: CodeRabbit scales agentic software development and ships 20x more
Its CEO estimates GPT-6 Astra caught about half the issues in CodeRabbit's internal review benchmark.
OpenAI published a customer story on CodeRabbit, which uses OpenAI models and Codex to review and govern AI-generated code. CEO Harjot Gill says Codex let the same team ship about 20 times more software over six months. He estimated GPT-6 Astra caught 50% of known issues in CodeRabbit's benchmark. CodeRabbit Secure uses Daybreak with Codex models to find and fix vulnerabilities.
Unconfirmed: Shipping volume, benchmark results, and vulnerability-fix claims come from CodeRabbit and its CEO, not independent verification.
- CodeRabbit says it is used by over 20,000 organizations and 150,000-plus open-source projects.
- Gill estimated he opened 2,500 to 3,000 pull requests in 30 days.
- GPT-6 Luna supports more subagents, while GPT-6 Astra handles planning.
- A Codex-powered Slack bot can return a pull request for incident triage.
- Vendors
- OpenAI
- Organizations
- CodeRabbit
- AI models
- GPT-6 AstraGPT-6 Luna
From the original article
6 min read at openai.comCodeRabbit uses OpenAI models to govern and trust AI-generated code and Codex to ship 20 times more software with the same engineering team.
openai.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.