Microsoft has announced the launch of MDASH, a multi-model agentic security platform designed to automate large-scale vulnerability discovery across Windows, Hyper-V, Azure, and other proprietary environments. The system represents a significant leap in AI-assisted cybersecurity, moving beyond single-model testing toward orchestrated frameworks that coordinate specialized agents for scanning, validation, debate, and proof generation.
MDASH integrates more than 100 AI agents, each tasked with distinct responsibilities such as deduplication, exploitation validation, and concurrency bug detection.
This architecture enables the system to reason across multiple files and determine whether vulnerabilities are practically exploitable rather than merely theoretical.
Microsoft reports that MDASH achieved an 88.45% score on the CyberGym benchmark of 1,507 real-world vulnerabilities, outperforming competitors by five points. Internally, it demonstrated 96% recall on historical clfs.sys vulnerabilities and 100% recall on tcpip.sys cases.
The company emphasizes that the orchestration layer, rather than raw model capability, will define the future of AI security tooling. MDASH is deliberately model-agnostic, allowing teams to swap or upgrade models while maintaining the surrounding validation and workflow infrastructure. .
AI in Coding
AI has steadily transformed software development over the past decade. Tools like GitHub Copilot and OpenAI Codex have introduced real-time code suggestions, automated debugging, and even autonomous coding agents.
These systems reduce developer workload, accelerate production cycles, and improve code quality. Yet, as AI becomes embedded in coding workflows, the risk of introducing subtle vulnerabilities has grown. MDASH reflects Microsoft’s recognition that AI must not only assist in writing code but also in auditing and securing it at scale.
Currently, MDASH is undergoing internal testing and limited private previews. Organizations interested in participating can apply through Microsoft Security’s preview program.
Image credit: Microsoft