# Google Cloud — Changing the game: Using agentic AI to secure infrastructure code

- Company: Google Cloud (cloud.google.com)
- Announced: 2026-09-19T01:00:00+00:00
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://cloud.google.com/blog/topics/systems/using-ai-agents-to-secure-google-infrastructure/
- Record: https://forck.live/items/17330-changing-the-game-using-agentic-ai-to-secure-infrastructure-code
- Subject: Gemini Enterprise

Google's AI and Infrastructure team developed AI-native agentic methods that embed vulnerability scanning and patching into its software development lifecycle. The system continuously scans every code change across hundreds of millions of lines of code, preventing hundreds of vulnerabilities per month from reaching production. The open-source multi-agent review harness Mantis was evolved to increase precision, achieving false-positive rates as low as 3% in some cases.

## Evidence

Verbatim from https://cloud.google.com/blog/topics/systems/using-ai-agents-to-secure-google-infrastructure/:

> By continuously scanning every code change across hundreds of millions of lines of code that we deploy onto our infrastructure, we are preventing hundreds of vulnerabilities per month from ever reaching our code base or production, defending our global network, AI infrastructure and our users.

---

Record: https://forck.live/items/17330-changing-the-game-using-agentic-ai-to-secure-infrastructure-code
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md