Traditional authentication is incapable of securing AI agents, the company says, as it announces Access Intelligence.

InfoWorld is a source of news, analysis, and commentary on technology trends, IT strategies, and business innovation. With a focus on enterprise technology and digital transformation, InfoWorld offers insights and guidance for IT decision-makers, software developers, and technology professionals. From  articles on cloud computing and cybersecurity to product reviews and industry trends, InfoWorld helps readers navigate the complexities of modern IT environments and make informed decisions to drive business success.

InfoWorld

Curity has announced Access Intelligence, an extension to its Identity Server platform that addresses the security gaps of traditional IAM when applied to AI agents. Unlike static, pre-granted permissions used in conventional IAM, Access Intelligence grants agent access at runtime using OAuth tokens that carry information about the agent's purpose and intent. Each action generates a separate token with specific permissions, and high-risk actions can require human authorization. The self-hosted microservice acts as an IAM layer through which every agent request must pass, isolating unregistered agents from real-world actions. Curity's CTO argues that traditional IAM tools, API gateways, and WAFs are inadequate for securing autonomous agents, and that no single solution can fully address agent security — multiple complementary layers are needed.

Curity looks to reinvent IAM with runtime authorization for AI agents