Zenity integrates its security and governance platform with Microsoft to provide real-time enforcement of AI agent behavior for enterprise security teams
Zenity, a leading end-to-end security and governance platform for AI agents, announced an inline prevention solution for Microsoft Foundry, created to meet enterprise security and compliance needs. This launch also marks the general availability of Zenity’s inline prevention capabilities for Microsoft Copilot Studio, enabling organizations to implement real-time controls on agents built, deployed and operated across the Microsoft agentic stack.
Also Read: CIO Influence Interview with Duncan Greatwood, CEO at Xage Security
Microsoft Foundry is rapidly evolving, delivering new and powerful features to help enterprises build, customize and deploy advanced agents that orchestrate AI across proprietary and public data, models, workflows and tools. Zenity’s collaboration with Foundry brings hard boundaries and runtime enforcement to AI agents. These capabilities are coming soon in preview and developed to meet enterprise standards for security and compliance. As these new Foundry features roll out, Zenity continues to enhance inline prevention for early adopters, ensuring easy governance in a dynamic development climate.
“Securing AI requires understanding of the intent and the full context of the agent,” said Michael Bargury, CTO and Co-Founder of Zenity. “Our work with Microsoft brings agent-centric security directly into Foundry Control Plane, giving enterprises deep visibility and governance, posture management, and real-time detection and inline response when it matters. Together, we’re enabling organizations to implement hard boundaries when adopting AI agents at scale – with the confidence that unsafe actions can be detected, analyzed, and disrupted before they cause harm.”
In addition to the preview capabilities introduced for Microsoft Foundry, Zenity’s integration with Microsoft Copilot Studio is now generally available. Copilot Studio empowers business and IT users to quickly create secure agents for workflow automation. Zenity delivers full lifecycle security, offering visibility, governance, vulnerability assessment and real-time threat detection for agents.
Zenity’s approach to agentic AI security, based on hard boundaries and deterministic runtime controls, includes:
- Hard boundaries that provide deterministic, real-time control of AI agent activities at runtime, enforcing strict policy compliance by preventing unsafe behaviors before they occur
- Comprehensive analysis of data flows and tool invocations tied to agents throughout their lifecycle
- Blocking attacks such as indirect prompt injection and data exfiltration by embedding enforcement directly in the agent execution path, removing ambiguity from agent behavior control
- Integration with Microsoft’s agent development ecosystem which empowers organizations to enforce immutable policy enforcement and hard stops on agent actions
Sarah Bird, Chief Product Officer of Responsible AI at Microsoft, said, “Zenity’s integration gives companies real-time control and visibility over the AI agents built with Microsoft Foundry and Copilot Studio. This lets security teams support innovation with the newest AI technologies while keeping data safe and meet compliance needs, helping companies create trustworthy AI agents at scale.”
As companies scale their use of agentic AI through platforms like Microsoft Foundry and Copilot Studio, they want to maintain security and governance. Zenity’s runtime enforcement, coupled with strong buildtime security posture management, gives security teams the tools to ensure agents operate in line with company policies, by design and at runtime, reducing risk and unlocking business innovation.
Catch more CIO Insights: The CIO’s Role In Data Democracy: Empowering Teams Without Losing Control
[To share your insights with us, please write to psen@itechseries.com ]
