New capabilities transform AI security from disconnected signals into continuous, contextual risk assessment, enabling security teams to understand and act on AI risk as it evolves

SAN FRANCISCO: #AIAgentSecuritySummit--RSA Conference - Zenity, the leading security and governance platform for AI agents in the enterprise, today announced continuous, contextual security for AI agents - a new approach that transforms how enterprise AI systems are secured and sets the foundation for Guardian Agents.

According to Gartner, “Guardian Agents represent the next evolution in AI governance, shifting from passive monitoring to active, real-time protection of AI systems.” Zenity’s continuous, contextual security delivers the foundational capabilities required to enable this shift.

AI agent risk doesn’t emerge in a single moment. It develops over time across configuration changes, runtime behavior, long-horizon tasks and interactions between agents, users and enterprise systems. Their behavior and exposure can shift in real time as agents rewrite instructions, update memory, and dynamically alter execution. Yet most security approaches, across legacy and startup solutions, still rely on snapshot posture scans and stateless prompt analysis, missing attacks that unfold across multiple interactions and leave teams with a view of risk that is outdated the moment it’s captured.

“Enterprise AI security is breaking under the current model. Agents don’t just execute, they reason, take action and evolve. As they do, risk evolves with them, continuously across every interaction and trigger,” said Ben Kliger, CEO of Zenity. “This release sets a new standard for securing agent-driven systems. Zenity is the first platform to unify posture, runtime behavior, and threat signals into a real-time view of risk. This is the architecture required to secure AI agents at scale, and we’ve built it.”

Zenity’s continuous, contextual security closes these gaps and lays the groundwork for Guardian Agents, enabling security teams to accurately identify, prioritize and respond to AI risk as it evolves across the enterprise. With Zenity, teams are empowered to:

• Detect evolving threats with agent context in mind with the stateful threat engine that analyzes full interaction chains in real time, across users, agents and sessions. This includes multi-step prompt injection, gradual data exfiltration and tool misuse that would otherwise appear benign.
• Maintain real-time exposure visibility by replacing periodic posture scans with real-time, event-driven ingestion that reflects configuration, permission, MCP, and connector changes as they occur, ensuring security teams operate on current risk.
• Prioritize what matters most with Issues Correlation Agent, connecting posture, runtime activity, and environmental signals into unified risk objects and allowing teams to identify where exposure and active behavior intersect.

By bringing together real-time exposure visibility, stateful runtime detection and contextual risk correlation into a unified model, Zenity moves beyond fragmented monitoring toward intelligent, adaptive security that understands how risk develops and evolves.

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.

Fonte: Business Wire