Glossary
These are the terms the HYPR AgentPass documentation uses, with a link to the page that covers each one.
| Term | Definition |
|---|---|
| Active role | The role a person who holds several works in, chosen under Viewing as. See Work in More Than One Role |
| Agent | Software that uses a model and tools to complete tasks. AgentPass™ governs local and provider-managed cloud agents |
| Agent Portal | A branded web experience where users interact with a published agent. See Agent Portal |
| Approval | A supervisor's decision to allow or deny a requested agent action. An approval is signed with a passkey when signed approvals are required. See Approving and Denying Agent Actions |
| Channel | A connection that carries messages between a supervisor and an agent. See Having Conversations with Your Agent |
| Connector | A configured path between AgentPass and an AI provider, MCP server, REST API, cloud-agent provider or communication channel. See Connectors |
| Data ceiling | The highest data classification a connector may receive. See A Connector's Data Ceiling |
| Endpoint Guard | The workstation client that discovers AI tools, and applies supported managed configuration. See Endpoint Guard |
| Enforce mode | A policy mode that applies allow, deny or approval decisions to live traffic. See How Policies Are Evaluated |
| Evaluator | A managed cloud agent assigned to review coding-agent sessions and return observations. See Session Watch |
| Forensics Store | Long-term storage for your organization's events, when your deployment has one connected. See Forensics Store |
| Managed cloud agent | An agent hosted by Anthropic or AWS Bedrock AgentCore, and governed through AgentPass. See Managed Cloud Agents |
| Observe mode | A policy mode that records what a policy would decide, without changing the request. See How Policies Are Evaluated |
| Onboarding mode | The connector setting that decides how AgentPass handles a caller without an approved identity. See Onboarding Mode |
| Policy | A condition and an action that allow, deny, observe or require approval for agent traffic. See Policies |
| Policy author | A managed cloud agent an administrator designates to draft policies. See Choosing Who Drafts Your Policies |
| Request Log | The console's record of the requests that pass through the gateway. See Viewing the Request Log |
| Role claim | The sign-in token claim whose values are mapped to AgentPass roles. See Populate Roles From Your Identity Provider |
| Service agent | A non-human identity with a named owner, its own role, a connector scope and an optional expiry. See Service Agents |
| Session | A correlated unit of agent work that joins related requests and tools into one record. See Agent Session Forensics |
| Subagent | An agent branch that performs part of a parent session's work. See Subagent Attribution |
| Supervisor | The person accountable for an agent's access and approval decisions. See the Supervisor Guide |
| Tag | A data category assigned to tools. A tag may carry a floor tier, the lowest tier anything carrying the tag can be. See Classifying the Data Your Tools Handle |
| Tier | A ranked data sensitivity level, such as Confidential. Policies compare tiers by rank. See Classifying the Data Your Tools Handle |