ToolsMay 14, 2026via The Decoder
Microsoft pits more than 100 AI agents against each other to find Windows vulnerabilities
Why it matters
Microsoft has moved AI agents from research to production security infrastructure, demonstrating real-world deployment at scale. This signals how enterprises are operationalizing multi-agent systems for critical business functions beyond chatbots.
Key signals
- Microsoft built MDASH, a system using 100+ specialized AI agents
- System uncovered 16 security flaws in Windows on Patch Tuesday
- 4 of the 16 flaws were critical severity
- Microsoft did not disclose which AI models power the system
- System uses adversarial agent approach (agents pit against each other)
The hook
Not a pilot. Microsoft deployed 100+ AI agents in production to find Windows vulnerabilities—16 flaws caught on Patch Tuesday alone.
Microsoft has built MDASH, a system that pits more than 100 specialized AI agents against each other to find software vulnerabilities. On Patch Tuesday alone, the system uncovered 16 security flaws in Windows, four of them critical. Microsoft isn't saying which AI models power the system.