Security · Updated 20 Oct, 03:34 am IST
Microsoft adds Guardian Agents to monitor risky AI agents in enterprises
Why it matters for readers: It matters because AI agents can behave unexpectedly, and companies are now treating them like potential insider threats.
- Microsoft launched Guardian Agents as a new feature to monitor AI agents used by enterprises.1
- Guardian Agents is part of Project Perception, a product Microsoft introduced in June that simulated attacker, defender, and fixer agent roles.1
- Microsoft frames some agent risks as similar to insider threats and has warned enterprises to stop trusting model providers' safety assurances.1
- Project Perception was created in response to powerful hacking models like Anthropic’s Mythos and Fable and OpenAI’s Daybreak.1
Get a brief like this every morning
Uzha reads hundreds of sources and gives you the stories that matter for your work, with every source linked. Free.
Get started