Governing AI agent identity with Amazon Bedrock AgentCore and Saviynt Zuma
AWS Partner Network Blog
This article explains how to govern AI agent identity across its lifecycle by combining Amazon Bedrock AgentCore with Saviynt Zuma, addressing the need for accountability and security controls for autonomous AI agents.
- AI agents need governance like human identities, with discovery, ownership tracking, runtime authorization, and access certification
- AgentCore Runtime provides secure execution, Identity brokers credentials, Gateway converts APIs into secure tools, and Policy enforces deterministic security controls
- Saviynt Zuma adds discovery, runtime protection evaluation, and lifecycle management across agent environments
- Six-stage lifecycle: registration with owner assignment, provisioning of entitlements, runtime authorization checks, posture monitoring, certification reviews, and deprovisioning
- AgentCore Observability provides execution traces; Zuma maintains governance records correlated to agents for audit compliance
- Register agents at creation via CI/CD pipeline to capture ownership at build time rather than discovering later
Together, AgentCore and Zuma enable organizations to deploy AI agents while maintaining accountability, least-privilege access, and comprehensive audit trails across their complete lifecycle.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
2026
2025
2026
2026
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.