Skip to main content
Version: 11.5.0

HYPR AgentPass: Overview

HYPR AgentPass

HYPR AgentPass™ is the trust layer for enterprise AI agents. It gives every agent a verifiable identity, routes its traffic through one gateway, and puts a person in charge of the actions that matter.

The Challenge​

Teams across your organization now build and run AI agents, from coding agents on workstations to agents on cloud platforms.

Most of these agents run without the controls you apply to people.

They often use shared credentials, can reach any tool those credentials allow, and work unattended, so no one approves a risky action before it happens.

The value of agents rises as they take on more autonomy, but only while you can still govern them. Without that control, the value levels off and then falls, as agents move from acting to running around the clock.

Business value plotted against agent autonomy, from Assist, Recommend and Act to Partial Autonomy and 24x7 Autonomy. With AgentPass, value keeps rising as autonomy grows. Without AgentPass, value levels off and declines beyond Act.

What HYPR AgentPass Can Do for You​

HYPR AgentPass binds each AI agent to an accountable person. It sits between your agents and the providers and tools they call. For every request, it:

  • Identifies the agent and its supervisor
  • Applies policy and tool permissions before the request runs
  • Holds high-risk actions for the supervisor's approval in the HYPR mobile app
  • Records every request for audit

It does this with the identity provider, model providers, and tools your teams already use.

AgentPass combines four capabilities.

The four HYPR AgentPass capabilities: Endpoint Enforcement, Forced Gateway Routing, Identity, Policy and Delegation, and Human Supervision. If it doesn't go through HYPR, it doesn't run.

The following table describes each capability, and links to its pages.

CapabilityWhat it does
Endpoint EnforcementDetects agent use on workstations and blocks unmanaged direct access to AI providers
Forced Gateway RoutingSends all agent traffic through the gateway for inspection and control
Identity, Policy and DelegationGives every agent a verifiable identity, scoped authority and a policy envelope
Human SupervisionRequires a person's approval for sensitive actions, and lets supervisors intervene or turn an agent off, even when the agent works unattended

Security Benefits to Your Organization​

AgentPass limits what each agent can reach, and records what it does. The following table lists what that gives your security team.

BenefitWhat it gives you
Policy enforcementStops unmanaged AI traffic from bypassing your policies, so agent activity stays compliant
Data protectionReduces sensitive data leaking to external services by classifying and inspecting what each call carries
Access controlEnforces least privilege for agent actions, and limits each agent to the tools its role is granted
Human approvalPuts a person in the loop for high-risk or ambiguous agent actions
Immediate kill switchTurns off or revokes any agent, taking effect on its very next request
Audit and investigationKeeps an end-to-end record of agent activity for compliance and security forensics

Next Steps​

  1. Read HYPR AgentPass: How It Works to follow a request through the gateway.

  2. Check the Prerequisites before you set anything up.

  3. Follow Your First Governed Agent to bring your first agents under AgentPass.

Start Here by Role​

Pick the guide that matches your job. Each one says what you can do, how AgentPass works from your seat, and what to try in your first hour.

You areStart with
The person who sets up the gateway, sign-in, connectors and rolesAdministrator
The person who runs the gateway day to dayOperator
In security operations, triaging alerts and investigating agentsSecurity Analyst
Checking configuration and collecting evidenceAuditor
Responsible for the models that guardrails consultModel Governance Owner
Responsible for one or more agents, approving what they doSupervisor
Using a coding agent, such as Claude Code, on a work computerDeveloper
Chatting with your organization's agents in a browserAgent Portal User

Common Jobs​

I want toGo to
Connect an AI provider, MCP server or REST APIConnectors
Decide who signs in, and with which roleRoles and Permissions
Bring the AI tools on our workstations under the gatewayGetting Started with Desktops
Point a coding agent at the gatewayOnboarding Your Agent
Require a person's approval for an actionRequire a Person for High-Value Agent Actions
Approve or deny a request on my phoneApproving and Denying Agent Actions
Stop an agent nowTurning Off an Agent
Find out why a request was blockedInvestigating a Policy Decision
Respond to an agent incident, from alert to evidenceRespond to an Agent Incident
Investigate what an agent did in a sessionAgent Session Forensics
Review which agents still need their accessRunning Agent Access Reviews
Send records to our SIEM, or export themData Management

Playbooks​

Playbooks walk through a complete use case in order. See AgentPass Playbooks for all of them.

What's New​

The Changelog lists the changes in each AgentPass version.