Tetrate and Ory Partner to Secure Enterprise AI Agents with Dynamic Policy Control

Jun 3, 2026
Tetrate and Ory have announced a joint solution that integrates Ory’s authorization platform with Tetrate Agent Router Enterprise to enforce dynamic, granular policy for AI agents in production environments.

Tetrate and Ory have announced a strategic partnership to enhance security for enterprise AI agents, according to a press release. The collaboration combines Ory’s identity and authorization engine with Tetrate Agent Router Enterprise, which is built on an Envoy-based AI gateway. The integrated system enforces dynamic policy on live MCP tool calls and their parameters.

The joint solution applies two layers of control. Tetrate manages enforcement at the network and gateway level by inspecting live traffic and tool requests, while Ory handles authorization and access decisions at the resource level. When a request exceeds a defined risk threshold, Tetrate can pause it, trigger an authentication flow through Ory, and issue temporary elevated access subject to approval.

Ory treats AI agents as verifiable identities, while Tetrate enforces policies on agent interactions with models, tools, and enterprise services. This includes parameter-level control over MCP tool calls. The system allows enterprises to define and apply least-privilege access policies through Ory Keto and to monitor agent activity for audit and compliance.

The solution is built on the Envoy AI Gateway, which supports distributed policy enforcement across multiple environments. It is available now, and both companies plan to collaborate on technical enablement, customer integrations, and demonstrations at Identiverse 2026.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Enterprise AI Brief, Cybersecurity AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

Cybersecurity AI Weekly

Weekly newsletter about AI in Cybersecurity.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.