Okta Integrates with AWS to Deliver the Identity Foundation for Secure, Production-Ready AI Agents

Okta for AI Agents integrates with Amazon Bedrock AgentCore

14 mayo 2026 Time to read: ~

Why this matters:

Most organizations are deploying AI agents without a governed identity, central visibility, consistent access policies, or ways to shut them down. Research shows that 69% of organizations report security concerns, including data leakage, over-privileged access, and unauthorized agent actions. These risks slow adoption and make security feel like a blocker.

Your security, IT, and product teams’ missions is two-pronged: scale agent deployments and uphold enterprise-grade security requirements. Without the right identity foundation, your teams begin custom coding for every secure hand-off between users and agents. Complexity quickly increases while innovation slows.

What we’re announcing:

Today, Okta is announcing a new integration with AWS to deliver the identity foundation for secure, production-ready AI agents. Okta for AI agents is the identity foundation for the agentic enterprise. It helps organizations discover and register known and unknown AI agents, standardize access, and govern access over time to mitigate the impact of rogue agent behavior. By combining AWS AI workloads with enterprise-grade identity security, customers can scale agents more efficiently and securely.

As a fully managed, enterprise-grade generative AI platform, Amazon Bedrock provides the critical infrastructure to rapidly build and deploy agents capable of seamlessly acting across tools, data, and workflows with built-in security, responsible AI, and scalability. As an identity provider integrated with Amazon Bedrock, developers can leverage Okta for AI Agents to secure these agents from the first line of code.

Secure AI agents across the enterprise

This integration lets developers use agents to assign identities and access policies to Amazon Bedrock agents, enabling organizations to centralize identity security, while Amazon Bedrock AgentCore orchestrates secure agent actions across distributed environments. Key features include:

  • Shadow AI Agent discovery
  • AI agent registration in Universal Directory
  • API access management, with least-privilege enforcement
  • Privileged credential management with automated rotation
  • System logs for full audit and SIEM integration

To learn more, visit our landing page to get started.

Continue your Identity journey