What was the impact of the AI solution?

Organizations gain confidence to deploy and scale AI agents securely on Microsoft Foundry. Risks such as sensitive data exposure, credential leaks, jailbreak attempts, and unauthorized tool use are mitigated in real time. Customers across multiple sectors including healthcare and finance benefit from secure AI agent deployment. Zenity expands Microsoft Foundry’s ecosystem by providing critical runtime security features for AI agents.

Rank#1,239of 3,449

Source

MicrosoftPilotEvidence: Low40/100

Zenity and Microsoft Partnership for Runtime Security of AI Agents in Microsoft Foundry

Use case typeAgent orchestrationUpdated Jun 13, 2026

Zenity integrated runtime security controls into Microsoft Azure AI Foundry to provide continuous, real-time inline protection for AI agents against runtime threats such as misuse, data leakage, and tool misuse. This integration helps enterprises securely scale AI agents built on Microsoft Foundry, blocking unsafe agent behaviors before data moves or tools execute. The runtime security covers models, tools, data, and enterprise systems, enforcing agent-aware context and behavioral policies to prevent sensitive data exposure, jailbreak attempts, and unauthorized tool use. Zenity’s solution is available via Azure Marketplace and supports various sectors including healthcare, finance, manufacturing, and public sector. This partnership extends Microsoft Foundry’s capabilities by enabling secure production deployment of autonomous AI agents with comprehensive runtime security governance.

Organization: Zenity
Industry: Healthcare
Location: United States
Published: March 2026

Reported outcomes

Strategic outcomes

New product / capabilityAdded inline runtime security controls for AI agentsRisk & complianceEnabled real-time prevention of agent runtime threatsCustomer experience & trustIncreased confidence in secure AI agent deploymentEcosystem & partnershipsExpanded Microsoft Foundry security ecosystem

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: Zenity
Provider: Microsoft
Maturity: Pilot
Linked source: Zenity

AI agents moving from pilot to production introduce runtime security risks like misuse, data leakage, and unauthorized tool use that traditional controls do not adequately mitigate

Customer identity supportedSource describes one deploymentMaturity supported

Primary read

Use case focus

Showing 2 of 2

1Security
2AI Agents

AI agents moving from pilot to production introduce runtime security risks like misuse, data leakage, and unauthorized tool use that traditional controls do not adequately mitigate.

Zenity integrated inline runtime security controls directly in the Microsoft Foundry agent execution path for real-time threat detection and prevention.
This approach provides end-to-end agent runtime coverage with inline prevention for multiple threat classes including sensitive data leakage and jailbreak attempts.
Agent-aware context and behavioral enforcement evaluates decisions and chained actions, rather than isolated prompts.
The security solution is accessible through Azure Marketplace, enabling enterprises to confidently scale AI agents with enforced security policies.

Technologies

Microsoft Azure AI Foundry

Organizations gain confidence to deploy and scale AI agents securely on Microsoft Foundry.
Risks such as sensitive data exposure, credential leaks, jailbreak attempts, and unauthorized tool use are mitigated in real time.
Customers across multiple sectors including healthcare and finance benefit from secure AI agent deployment.
Zenity expands Microsoft Foundry’s ecosystem by providing critical runtime security features for AI agents.

Sources & evidence1

Evidence: Low40/100Evidence strength