Microsoft expands MDASH security platform with 100+ AI threat-hunting agents at Build 2026
Yesterday's bagel. Skim it, don't savour it.
Summary
Microsoft is expanding MDASH (Multi-model Agentic Scanning Harness) from preview into a full enterprise security control plane, connecting Defender, GitHub Code Security, Agent 365, and Purview. The system uses AI agents to filter security scanner noise, reducing thousands of alerts down to only exploitable vulnerabilities. At Build 2026, Microsoft positions agentic systems as the key advantage for enterprise-scale AI vulnerability discovery, addressing the signal-to-noise problem in security scanning.
Key quotes
· 4 pulledMicrosoft introduced MDASH as a multi-model agentic scanning harness to reduce security alerts by filtering constant scanner noise down to exploitable vulnerabilities.
At Build 2026, Microsoft is folding MDASH capability into an enterprise security control plane that connects Defender, GitHub Code Security, Agent 365, and Purview.
The approach targets the signal-to-noise problem where scanners can produce hundreds or thousands of red flags, many not warranting urgent response.
Agentic systems around the model are positioned as the durable advantage for enterprise-scale AI vulnerability discovery.
You might also wanna read
Study finds well-written AGENTS.md files significantly boost AI code generation, while poor ones hurt performance
A systematic study of AGENTS.md files across a monorepo reveals that well-crafted files can dramatically improve AI code generation quality
Augment Code·1mo ago
Research Study: AI Agents vs Human Cybersecurity Professionals in Penetration Testing
This research paper presents the first comprehensive evaluation comparing AI agents to human cybersecurity professionals in real-world penet
arxiv.org·5mo ago
Microsoft launches Scout, an autonomous AI agent for Microsoft 365 built on OpenClaw
Microsoft has unveiled Scout, an autonomous AI agent built on OpenClaw that operates as part of Microsoft 365. Scout acts on a user's behalf
computerworld.com·10d ago
Security Vulnerabilities in Agentic AI Browsers: Testing Reveals Scam Susceptibility
The article examines the emerging security vulnerabilities in agentic AI browsers that autonomously browse, search, and interact online. It
guard.io·9mo ago
Microsoft Launches Agent 365 Platform for Business AI Agent Management
Microsoft is launching Agent 365, a platform that enables businesses to build, manage, and control AI agents similarly to how they manage hu
The Verge·6mo ago
Emdash: Open-Source Agentic Development Environment for Running Multiple Coding AI Agents in Parallel
Emdash is an open-source Agentic Development Environment (ADE) that enables developers to run multiple coding AI agents in parallel, each is
github.com·3mo ago