Zenity Announces Availability of Inline Agent Runtime Security for Agents Built on Microsoft Foundry

Zenity, the leading end-to-end security and governance platform for AI agents, announced the general availability of runtime security controls for AI agents built on Microsoft Foundry as part of an expanded partnership with Microsoft. Building on the inline prevention capabilities announced this past November, this integration enables enterprises to safely deploy and scale Foundry applications and agents by delivering continuous, inline protection against runtime threats.

Also Read: AiThority Interview with Glenn Jocher, Founder & CEO, Ultralytics

“This expanded partnership with Microsoft allows customers to build and run AI agents in production with confidence, with capabilities that block agent misuse in real-time, before data moves or tools execute.”

As organizations move from experimentation to production, security risks are shifting from model development to real-time execution. Agents increasingly make decisions, chain actions, and invoke tools across enterprise environments. These behaviors introduce new classes of risk that traditional, prompt-level or post-execution controls were not designed to address.

“With agents, risks emerge and persist at runtime,” said Michael Bargury, CTO and co-founder of Zenity. “This expanded partnership with Microsoft allows customers to build and run AI agents in production with confidence, with capabilities that block agent misuse in real-time, before data moves or tools execute.”

Growing customer adoption of homegrown agents has increased demand for production‑ready protections that understand agentic behavior and intent. The expanded Zenity and Microsoft Foundry integration delivers:

• End-to-end agent runtime coverage across models, tools, data and enterprise systems
• Inline prevention for multiple threat classes, including sensitive data leakage, secret and credential exposure, jailbreak attempts and tool misuse (coming soon)
• Agent-aware context and behavioral enforcement that evaluates decisions and chained actions rather than isolated prompts

Together, these capabilities help organizations move beyond point solutions toward a more comprehensive approach to securing agents in production.

Customers are building and deploying agents on Microsoft Foundry across IT operations, customer support, finance, healthcare, manufacturing, and the public sector. These agents often connect directly to enterprise resources such as SharePoint, OneDrive, databases, SaaS platforms, and internal APIs. While this connectivity unlocks significant business value, it also increases exposure when agents are misconfigured, manipulated, or abused at runtime.

Zenity integrates natively into the agent execution path within Foundry, enabling security teams to detect, disrupt, and prevent threats as they occur, before data is exposed, tools are misused, or systems are impacted.

“Inline security only works if it’s part of the execution path,” Bargury added. “Zenity integrates where agents actually operate, ensuring that autonomy doesn’t come at the cost of security or compliance.”

Also Read: ​​The Infrastructure War Behind the AI Boom

[To share your insights with us, please write to psen@itechseries.com]