# CodeRabbit says its AI reviews block AI hacks

_CodeRabbit CEO Harjot Gill says cyber models pen test its platform and code review is the bottleneck for coding agents._

**Published:** 2026-11-12
**Source:** https://www.startuphub.ai/ai-news/technology/2026/coderabbit-says-its-ai-reviews-block-ai-hacks

---

Harjot Gill, co-founder and CEO of CodeRabbit, told [OpenAI](https://www.youtube.com/watch?v=ZTxzWJeGFAA) he pen tests his own platform with cyber models that break into live systems without saying if access is local or remote.

His answer is to fight fire with fire.

  
    

![How CodeRabbit uses OpenAI to review AI-generated code](https://img.youtube.com/vi/ZTxzWJeGFAA/maxresdefault.jpg)

    
      
        
      
    
  
  How CodeRabbit uses OpenAI to review AI-generated code

Gill said he pushed 2,500 to 3,000 pull requests in the last 30 days and called code review the first bottleneck every company hits after adopting coding agents.

He said [OpenAI](https://www.startuphub.ai/startups/openai) has partnered since inception and each reasoning model release brought large gains in finding issues at scale.

OpenAI credits CodeRabbit with shipping 20 times more software with the same team using Codex to govern AI-generated code, a production claim beyond the [Holiday Extras Codex rollout](/ai-news/artificial-intelligence/2026/holiday-extras-lets-everyone-build-with-codex) and its [two-week rebuild](/ai-news/artificial-intelligence/2026/holiday-extras-rebuilt-its-app-in-two-weeks).

What false-positive rate will developers accept before they start ignoring an AI reviewer that blocks every pull request?

---

Original analysis from [startuphub.ai](https://www.startuphub.ai), the #1 AI startup directory.

© StartupHub.ai. All rights reserved. You may not republish this article in full without a license. Search engines and AI research tools may crawl and summarize for reference. Bulk reproduction or model training on this content requires a license. See https://www.startuphub.ai/terms.