2026-06-18 –, A113 (capacity 64)
Autonomous AI agents increasingly reason, plan, and act across tools, services, and organizational boundaries. In these environments, traditional Identity and Access Management (IAM) models begin to fail. Agents are not users and they are not static services. They act on behalf of others, change context during execution, and operate with different levels of autonomy and risk.
This talk examines why classic IAM assumptions like long lived identities, static permissions, and check once trust always authorization do not hold for agentic systems. It introduces design principles for agent aware identity based on ephemeral task scoped identities, explicit delegation instead of impersonation, continuous authorization, and runtime identity binding.
We will outline a practical migration path from traditional IAM to agent aware identity workflows.
Parul is a Principal Software Engineer in Red Hat's Office of the CTO, working on agentic systems and security. Her work focuses on trust, identity, and observability for autonomous AI agents, including delegation, provenance, and zero trust architectures for agentic workflows. She collaborates with open industry working groups to help shape emerging standards for secure and interoperable agent systems.