Recently, Zenity, a security and governance platform provider for AI agents, announced that it would be expanding its integration with Microsoft to deliver native, inline attack prevention for Microsoft Copilot Studio agents.
How Zenity enables deploying agentic AI at scale
The integration will enable organizations to deploy agentic AI at scale with greater control and security.
“This integration marks a major step forward in enabling secure and scalable AI innovation for enterprises,” said Shay Gadidi, vice president of product management at Zenity. “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.”
Zenity will now be able to operate within each agent built in Copilot Studio. This will provide inline controls for tool invocation, such as MCP servers, CRM systems, business applications, and email, to prevent data exfiltration, direct and indirect prompt injections, and improper handling of secrets.
As part of the integration, organizations can now apply native security controls as the backbone for expanding Copilot Studio across departments and users. This application capability will help ensure that as agents are created, they remain within approved boundaries, comply with enterprise policies, and are natively monitored in real time to help disrupt and block attacks.
Highlights and benefits of the expanding integration
Among the key highlights of the integration that provides in-depth security and protection from existing and emerging threats across agents include:
- Real-time threat disruption & prevention: Zenity helps block actions that show signs of potential security risks, both in-line and in real-time, by analyzing intent and behavior signals before they are completed.
- StepLevel monitoring & policy enforcement: Microsoft and Zenity will work to provide customers with a full execution context for every agent, ensuring compliance and enabling automated enforcement of enterprise policies.
- Continuous enterprise visibility: These inline threat prevention capabilities extend Zenity’s platform to deliver broader threat analysis, more advanced intelligent threat reasoning, and robust threat disruption into AI agent activity.
In terms of benefits from this expanded integration, customers can expect the following:
- Scaling Copilot Studio across business units: Marketing, HR, finance, and operations teams can build agents while maintaining centralized security and governance.
- Inline attack disruption & prevention: Minimizes the risk of breaches, data loss, or policy violations without disrupting workflows.
- Understanding agents’ behavior and intent: Ensure proper configuration from the start, accelerating deployment and productivity, and gaining deep insights into how agents are built and customized in Copilot Studio.
“With this integration with Zenity, we’re making it easier for enterprises to confidently scale AI agent development across their organizations,” said Shay Gurman, vice president, Microsoft Copilot Studio. “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.”
AI agents are increasingly prevalent in the channel to help organizations automate tasks and help customers. Read more about Druva’s latest agentic AI expansion to automate security tasks, speed recovery, and manage cyber threats.