Amazon launches IAM service for AI agent security and access control
Amazon's new Bedrock AgentCore Identity service centralizes AI agent identity management, credential security, and AWS integration for scalable access control.
Amazon has launched Bedrock AgentCore Identity, a new identity and access management (IAM) service designed specifically for AI agents. The service aims to streamline the management of agent identities, secure credentials, and enable seamless integration with both AWS and third-party services.
Key Features of AgentCore Identity
- Centralized Identity Management: Provides a unified directory for creating and managing agent and workload identities.
- Dual Authentication Model:
- Inbound: Controls who can access the agent.
- Outbound: Manages what resources the agent can access.
- Resource Credential Provider: Stores configurations for agents needing credentials to access downstream services like Google or GitHub.
- Resource Token Vault: Securely stores user OAuth tokens for agent actions on behalf of users.
Benefits and Claims
Amazon asserts that the service eliminates months of custom development by offering enterprise-grade security. It enables AI systems to "safely operate across organizational boundaries" while accessing diverse resources. The service is particularly relevant for integrations with platforms like Salesforce, Slack, and other third-party tools.
Availability
Detailed documentation is available on the AWS Bedrock AgentCore page. The launch reflects Amazon's continued investment in agentic AI infrastructure and security solutions.
Related News
Preventing rogue AI agents from causing harm
Agentic AI is making decisions and taking actions for users, but safeguards are needed to prevent misuse and errors.
How Frontier Firms Leverage Microsoft Azure for AI and Cloud Modernization
Discover how Frontier Firms are scaling AI transformation with human-agent teams and modernizing their infrastructure on Microsoft Azure for competitive advantage.
About the Author

Alex Thompson
AI Technology Editor
Senior technology editor specializing in AI and machine learning content creation for 8 years. Former technical editor at AI Magazine, now provides technical documentation and content strategy services for multiple AI companies. Excels at transforming complex AI technical concepts into accessible content.