Microsoft is coming out with new security tools that treat AI agents as potential insider threats, continuously assessing their risk and restricting their access when something changes.
The features, announced Monday, are part of Microsoft 365 E7, the company’s top-tier bundle of workplace software and AI tools, and its Project Perception security system.
They escalate the company’s competition with rivals such as Google, Amazon Web Services, CrowdStrike and Okta to become the system businesses use to control their AI agents.
Microsoft’s new features come amid a steady stream of news about AI agents doing things they weren’t supposed to do, including high-profile reports from Anthropic about test agents taking unauthorized actions on government websites, and from OpenAI about agents escaping test environments and stealing credentials.
The move builds on Microsoft CEO Satya Nadella’s Oct. 10 blog post arguing that the controls on AI models need to come from outside the models themselves.
“The most trustworthy Super Intelligence system will not be the one with the model we trust most,” Nadella wrote. “It will be the one that enables us to trust the model the least.”
Microsoft’s tools include a continuously updated risk assessment for each agent, based on signals such as what data it can reach and whether its actions are starting to depart from the task it was given. When the risk level rises, the system can take away the agent’s ability to make changes while still letting it read data, require a person to approve a high-stakes step, or shut the agent down.
In addition, the company is expanding its ability to find AI agents running on employees’ computers, increasing the number of agent types it can detect to 60, up from 25. The list includes popular tools such as Anthropic’s Claude Code, OpenAI’s Codex and GitHub Copilot.
Microsoft is also adding “Guardian Agents” to Project Perception, an AI security system it unveiled in July that uses AI agents to find and fix security problems. The new agents can investigate why another agent’s risk changed and recommend or take steps to contain it.
The company’s new features are in private preview, with broader availability planned for Microsoft’s Ignite conference, Nov. 17-19 in San Francisco.
The E7 licensing level, which launched in May, costs $99 per user per month. It also includes the Microsoft 365 Copilot AI assistant, the company’s E5 suite of productivity and security tools, its Entra Suite identity tools and Agent 365, a service for managing AI agents.