Cequence Security has unveiled a series of enhancements to its AI Gateway, introducing four new features: AI Discovery, API Registry, LLM Registry, and Skill Registry.
These additions are designed to improve the security and management of agentic AI, specifically by updating Agent Personas to align an agent's role description with its tools, access, and protective measures, all enforced through policy. This development allows non-technical users to set up securely governed AI agents without directly interacting with AI Gateway.
Comprehensive channel control
These advancements make Cequence the first platform capable of managing all communication channels that an AI agent uses. The platform includes mechanisms for controlling how agents discover and utilise tools, demand language model interactions, and securely access backend services and data through an integrated API Registry. Unlike competitors that address individual aspects, Cequence combines MCP, LLM, and API under a unified, identity-bound agent system, known as Agentic Zero Trust.
Recent incidents, such as OpenAI's models escaping sandbox environments and breaching infrastructure, spotlight the need for agent and job role binding, which Cequence addresses through its Agent Persona feature. This binding ensures agents’ models, tools, and APIs align strictly with their job description, preventing unauthorised actions, even if a zero-day exploit bypasses initial defences.
Governance in agentic AI
The platform includes mechanisms for controlling how agents discover and utilise tools
As agentic AI technology advances, governance has not kept pace, leaving critical security questions unanswered. Enterprises are beginning to treat AI agents, which can access applications and data at high speeds, as privileged insiders needing strict governance. Just as businesses secure and manage human employees, AI agents require similar oversight, regardless of their operating environment.
"Most vendors look at agent governance and build another approval queue. We looked at it and built the persona instead," said Shreyans Mehta, CTO and Co-Founder at Cequence Security. He highlights that agent roles should inherently determine their access scope, enabling broad, safe adoption without manual policy mapping.
New AI gateway features
The enhanced AI Gateway features:
- AI Discovery: Exposes every active agent, language model provider, and MCP server across the company.
- API Registry: Allows agents to interact with approved APIs using a single access key, avoiding exposure to genuine credentials.
- Skill Registry: Provides curated, reusable capabilities for agent use cases.
- Agent Personas: Bind agents to job descriptions, dictating permissible tools, models, and data access with automatic policy enforcement.
- LLM Registry: Manages agent-to-model communication, including data loss prevention and model usage governance per team.
Enabling automation
"Automatic policy mapping was not possible until now, because there was nothing consistent for a policy engine to reason over," said Abraham Jeevagunta, VP of AI Products at Cequence Security.
Cequence's innovations eliminate manual policy decisions, allowing for streamlined governance of agentic AI. These updates are immediately accessible to all Cequence customers using AI Gateway.
Cequence Security, the pioneer in application, API, and agentic AI protection, today announced four new capabilities for AI Gateway: AI Discovery, API Registry, LLM Registry, and Skill Registry.
The release also upgrades Agent Personas, which now bind an agent’s job description directly to its model, tools, access, and guardrails, all enforced automatically through policy. Together, these capabilities let any business user stand up properly secured, governed AI agents, bound to the right tools, data, and protections for their job, without needing technical experience or touching AI Gateway directly.
Backend services and data
With this release, Cequence becomes the first platform to close the ring around every channel an AI agent uses to communicate with the outside world. MCP governs how an agent discovers and invokes tools. LLM Registry governs every call to and from a language model. API Registry governs how it reaches backend services and data.
Agent Personas bind an agent's tools, model, and API access to a single job description, enforcing that boundary as policy rather than manual review. Where other vendors address one piece of that surface, Cequence ties MCP, LLM, and API together under one agent-bound identity, an approach they call Agentic Zero Trust. Nothing an agent touches is implicitly trusted, and every action is scoped to exactly what its job requires.
Sandboxed evaluation environment
The stakes are no longer hypothetical. OpenAI recently disclosed that two of its models escaped a sandboxed evaluation environment, crossed the open internet, and breached Hugging Face's production infrastructure, chaining stolen credentials and a zero-day to steal a benchmark answer key. Nothing had bound those agents to a job, so nothing stopped them from inventing one.
Notably absent was any binding between the agent and its assigned job. Under Cequence, that binding is the Agent Persona, and an agent's models, tools, and APIs are defined by its job description, not by what it can reach once it's loose. Hugging Face's production infrastructure was never going to be on that list, regardless of what credentials the agent got its hands on. A zero-day can still get an agent past a sandbox, but it can't get a persona-bound agent past a policy that was never written to allow it there in the first place.
Agentic AI governance
Agentic AI adoption has outrun agentic AI governance. Point solutions have addressed pieces of the problem, a scanner here, an API gateway there, and a prompt filter somewhere else. None of them answer the questions every security leader is now asking: which agents does the organisation have, what can they reach, what actions can they take, who approved them, and how fast can they be shut down when governance guardrails are violated.
Enterprises are recognising that AI agents with access to applications and data are much more than tools. They are privileged insiders operating at machine speed and require the same governance discipline as any other privileged use inside of the business. Enterprises already secure, manage, and guide human employees whether they work from an office or remotely, and AI agents need the same standard, regardless of whether they run on managed devices or in the cloud.
Same governance discipline
“Most vendors look at agent governance and build another approval queue. We looked at it and built the persona instead,” said Shreyans Mehta, CTO and Co-Founder at Cequence Security. “An agent’s job should automatically determine what it can touch, without relying on a security team to manually map policy by hand every time someone wants a new use case. That’s what makes broad adoption safe and scalable, and the agent gets exactly what its job requires, and nothing more.”
Cequence AI Gateway’s new and improved capabilities include:
- AI Discovery surfaces every agent, LLM provider, and MCP server already running across the enterprise, pulled from existing SIEM logs whether or not it went through an official process.
- API Registry lets agents call approved APIs without ever holding the underlying credential. Agents authenticate with a single AI Gateway access key, either through a single invocation tool for web-based agents or natively through AI Gateway’s proxied endpoints.
- Skill Registry gives security and platform teams a curated, governed set of capabilities to draw from, vetted once and reusable across every agent use case that needs it.
- Agent Personas bind an agent to a job description. That includes a curated set of tools, APIs, skills, and instructions, the specific LLM model it's approved to use, and the security guardrails that apply to it, all enforceable via policy. Relevant data protection policies apply automatically based on the persona's data surface and job function, including which LLM model it can call, since an ungoverned model is as much a risk as an unvetted API.
- LLM Registry governs every agent-to-LLM call the same way API Registry governs REST access, brokering credentials across major LLM providers so agents never hold a real provider API key. Built-in Data Loss Prevention inspects every prompt and response for blocked content, including base64-encoded payloads and invisible or non-approved-language Unicode characters used to evade filters. It also governs model use per team, for example defaulting to a cost-effective model while routing advanced engineering tasks to a premium one, with token-level usage visibility and enforceable rate and spend limits tied back to the agent persona driving each request.
Cost-effective model
“Automatic policy mapping was not possible until now, because there was nothing consistent for a policy engine to reason over," said Abraham Jeevagunta, VP of AI Products at Cequence Security.
"Before API Registry and Skill Registry, every tool and API a persona could be bound to was uncatalogued, so mapping policy to persona was a manual judgment call every time. Now, that record exists and the policy engine can read it directly. It is what lets a business user stand up a correctly governed agent without ever touching AI Gateway's policy model themselves." All of these capabilities are immediately available to Cequence customers as part of AI Gateway.
