Home

Zenity Announces Full-Lifecycle Security and Governance for Amazon Bedrock AgentCore to Protect Enterprise AI Agents

via Business Wire

Integration and AWS Marketplace availability give customers visibility and control over AI agents built on AgentCore

Zenity, the leading security and governance platform for AI agents, today announced native support for Amazon Bedrock AgentCore, enabling enterprises to securely build, deploy, and manage homegrown AI agents across the AWS ecosystem. With this integration, Zenity is the first to provide full-lifecycle coverage for organizations adopting agentic AI on AWS, from secure development to runtime detection and inline enforcement. Amazon AgentCore customers will also soon be able to discover and deploy Zenity instantly via AWS Marketplace.

AgentCore is a powerful framework that gives developers the flexibility to build highly customized agents. AgentCore offers developers deeper control over memory, identity, orchestration, SDK behavior and the entire runtime environment. Zenity’s partnership with Amazon Bedrock AgentCore brings end-to-end security capabilities that AWS customers need as they scale their adoption of agentic AI; ensuring agents behave as intended, use tools safely, and operate within defined enterprise policies.

This integration enables joint Zenity and AgentCore customers to:

  • Gain an in-depth look and understanding of which agents exist and how they behave in enterprise environments
  • Detect and prevent unsafe agent behaviors like indirect prompt injection or unauthorized memory access in real time
  • Control agents built on AgentCore to ensure they cannot perform unsafe or unsanctioned actions, even as their behaviors evolve
  • Trace and map memory usage, toolchains, code instrumentation, and orchestration patterns back to enterprise policies and risk models

Because AgentCore agents are flexible, code-driven configurations, AWS does not automatically infer or visualize why an agent uses a particular capability, such as memory, Modern Context Protocol (MCP) or a privileged tool. Zenity fills this critical gap by giving security teams the complete picture of agent behavior and intent and helping prevent malicious or unintended actions before they can introduce risk.

“AgentCore provides a powerful and easy-to-use platform for developer-led agent development, and our integration ensures that security keeps pace with this innovation,” said Michael Bargury, CTO and co-founder of Zenity. “By connecting build-time configuration with live runtime telemetry, Zenity gives security teams complete visibility into agentic intent and full control over agentic behavior. This allows enterprises to detect, analyze, and prevent rogue agents before they introduce risk.”

Zenity provides the industry’s only agent-centric security platform for AgentCore that:

  • Delivers end-to-end visibility that reduces blind spots and unknown risk
  • Catches unsafe or anomalous actions in real time to prevent incidents
  • Blocks harmful behaviors deterministically to minimize business and compliance impact
  • Fits naturally into AWS developer workflows to accelerate secure, compliant adoption

With Zenity and AgentCore, enterprises can confidently scale their agentic AI initiatives while meeting their security, compliance, and governance obligations.

About Zenity

Zenity is the first security and governance platform purpose built for AI agents spanning SaaS, home grown platforms (Cloud) and end user devices (Endpoint). Trusted by Fortune 500 enterprises, Zenity helps security teams confidently adopt AI by delivering defense in depth with full lifecycle coverage, from agent discovery and posture management to real time detection, inline prevention and response. With an agent centric approach that prioritizes how agents behave, what they access and which tools they invoke, Zenity eliminates blind spots and enforces consistent policy and controls across environments so organizations can innovate with AI without compromising security. Learn more at www.zenity.io.

Contacts