Zenity has expanded its collaboration with Microsoft to embed native, inline attack prevention directly into agents built using Microsoft Copilot Studio, aiming to bolster security and control for organizations deploying agentic AI at scale. The integration is designed to facilitate secure and scalable AI agent deployment for enterprises.
As part of this expanded relationship, Zenity now operates within each agent developed in Copilot Studio. This functionality provides inline controls for tool invocation across various systems, including MCP servers, CRM platforms, business applications, and email. These controls are designed to prevent data exfiltration, direct and indirect prompt injections, and improper handling of secrets. Zenity’s platform offers end-to-end security, covering both build time and runtime, to mitigate malicious intent, suspicious behaviors, and unauthorized activities before they cause damage.
Organizations can now implement native security controls as a foundational element for extending Copilot Studio across different departments and lines of business. This ensures that newly created agents adhere to approved boundaries, comply with enterprise policies, and are continuously monitored in real time to detect and block attacks.
Shay Gadidi, Vice President of Product Management at Zenity, stated, “This integration marks a major step forward in enabling secure and scalable AI innovation for enterprises. By combining Microsoft Copilot Studio’s flexibility with Zenity’s security-first approach now incorporated into inline behaviors and actions of agents, businesses can confidently deploy AI agents without sacrificing control.”
Shay Gurman, Vice President, Microsoft Copilot Studio, commented, “With this integration with Zenity, we’re making it easier for enterprises to confidently scale AI agent development across their organizations. Together, we are combining Microsoft Copilot Studio’s intuitive agent-building experience with secure inline risk prevention. In doing so, we are empowering more users, from professional developers to business users, to innovate safely and responsibly while maintaining the security and governance that enterprises expect.”
The expanded integration offers several key features, including real-time threat disruption and prevention, which blocks potentially risky actions inline by analyzing intent and behavior signals. It also provides step-level monitoring and policy enforcement, giving customers full execution context for every agent to ensure compliance and enable automated policy enforcement. Furthermore, the inline threat prevention capabilities enhance Zenity’s platform to deliver broader threat analysis, more advanced intelligent threat reasoning, and robust threat disruption within AI agent activities.
Customers can anticipate benefits such as scaling Copilot Studio across various business units like marketing, HR, finance, and operations while maintaining centralized security and governance. The inline attack disruption and prevention minimizes the risk of breaches, data loss, or policy violations without disrupting workflows. Additionally, understanding an agent’s behavior and intent helps ensure proper configuration, accelerating deployment and productivity while providing insights into agent construction and customization in Copilot Studio.
This integration is currently available in public preview through the Zenity listing on Azure Marketplace.
