Identity Is the Bottleneck: Why Agents Force a New Security Model

AI Security & Safety

Agents don’t just call APIs. They plan, iterate, and take action across systems. As they move into real workflows, they expose a core issue: identity and access systems weren’t built for software that behaves like this. The current model assumes stable actors, predictable workflows, and permissions defined ahead of time. Agents don’t fit that model. They’re dynamic, they cross boundaries, and they operate in ways that can’t be fully anticipated.

This talk breaks down where that gap shows up and why it matters. It then looks at what needs to change. Identity becomes the control plane, with access decisions made at execution time using the full context of the user, the agent, and the environment, and enforced on every action.

Co-Founder

Jared Hanson

Keycard

Jared was the Chief Architect at Auth0 before joining Okta as a senior technical leader, and he created Passport.js, the most popular authentication framework for Node.js, downloaded millions of times every week.

Jared went on to co-found Keycard, the leading provider of the identity and access platform for AI agents.

With AI agents now taking on real-world actions and accessing real systems, Jared sees the identity problem as the defining infrastructure challenge of the moment — and he's building Keycard to solve it.

2026 Talks

Identity Is the Bottleneck: Why Agents Force a New Security Model

AI Security & Safety

The AI Conference for Humans Who Ship