Skip to main content
Version: 11.5.0

Cloud Agents: Overview

A cloud agent is an AI agent that runs on a provider's infrastructure instead of on somebody's workstation. Examples are Anthropic's Managed Agents platform and AWS Bedrock AgentCore in your own AWS account.

HYPR AgentPass™ governs these agents like the rest of your agent traffic. Every tool call the agent makes routes back through the gateway.

At the gateway, your policies decide the call, approvals gate it and the audit trail records it.

The result is an agent your organization can chat with, schedule and govern. The agent holds no standing credentials of its own, and its tool access stays inside your controls.

The following diagram shows that path, from whoever starts the agent to the tools it calls.

Chat, automations and assigned people start the agent. The provider, Anthropic or AWS Bedrock AgentCore, runs it with no standing credentials. Every tool call passes the AgentPass gateway, where policy decides, approval gates and the Request Log records. Only connectors on the agent's list, MCP servers and REST APIs, are reachable

AgentPass supports three providers, and each reaches AgentPass differently.

ProviderWhere the agent runsHow it gets into AgentPass
AnthropicAnthropic's Managed Agents platformYou create it in AgentPass from a template, a model, a prompt and tools. AgentPass provisions it on Anthropic. See Anthropic Cloud Agents
AWS Bedrock AgentCoreAgentCore in your own AWS accountYour team builds it in AWS. AgentPass imports it through a connector, then invokes and governs it. See AWS Bedrock AgentCore Agents
Microsoft 365 CopilotMicrosoft's cloudYou connect it by registering Copilot Studio agents on the connector. People reach them through the Agent Portal. See Microsoft 365 Copilot Agents

For Anthropic and AWS Bedrock agents, that is the only difference you notice. Once an agent exists, everything is uniform: the same chat, automations, assignments, enable switch and governance.

Microsoft 365 Copilot agents are managed on their connector, and people reach them through the Agent Portal.

Set Up a Managed Cloud Agent​

Each agent type arrives in its own way. Start from its setup procedure, as listed in the following table.

Agent typeHow it arrivesWhere to start
Anthropic, new agentCreate: New agent → New cloud agentSet Up an Anthropic Cloud Agent
Anthropic, built in the Anthropic consoleImport: Import agents, then sync the Anthropic Managed Agents connectorSet Up an Anthropic Cloud Agent
AWS Bedrock AgentCoreImport: create the connector, then sync it from Import agentsSet Up an AWS Bedrock AgentCore Agent
Microsoft 365 CopilotConnect: register Copilot Studio agents on the connectorSet Up Microsoft 365 Copilot

Where They Live in the Console​

Open Agents in the administration console, and set Runs to Cloud. Anthropic and AWS Bedrock agents appear in one list with the rest of your agents.

To see one provider, click its provider filter. See Find an Agent.

Needs attention marks a workload agent whose credential has expired, or an AWS Bedrock agent whose import has a conflict to resolve. Click Details on its row to see what to do. See Why It Needs Attention.

The providers differ in how an agent arrives:

  • Anthropic. Create the agent with New agent → New cloud agent. Agents already built in the Anthropic console arrive by import: open Import agents, and click the sync button beside your Anthropic Managed Agents connector.

  • AWS Bedrock. Agents arrive by import. Open Import agents, and click the sync button beside your AgentCore connector.

See Import and Create Agents.

Workload agents share this list

Workload agents appear on the same page, created with New agent → New workload agent. To list only them, set Acts as to Workload.

They are machine callers that hold a gateway credential but are not conversational, so they have no chat or automations. See Workload Agents.

The Agent Detail Page​

To open an agent's detail page, click ⋮ on its row on the Agents page, then click Manage. Manage in the agent's details opens it too.

The tabs depend on what the agent supports, as described in the following table.

TabWhat it holds
OverviewProvider, owner, where it runs (On a machine or In the cloud), whom it acts as, model or AWS account, description, tools, and how the agent was acquired: Created in HYPR or Synced from provider
ChatA direct conversation with the agent. Use it to test a new agent before anyone else does. Anthropic and AWS Bedrock agents only
AutomationsRuns on a schedule. Anthropic and AWS Bedrock agents only. See Automating Cloud Agents
AssignmentsWhich users and groups may use the agent. Not shown for workload agents
ActivityThe agent's recent tool calls. See The Activity Tab
CredentialThe workload agent's gateway credential. Workload agents only. See Managing Workload Agents
ToolsThe connectors the agent may call. For AWS Bedrock agents, also the credential that lets it call them. Anthropic and AWS Bedrock agents only

The page header carries the agent's controls:

A cloud agent's page, with its provider tag, the Change stage button, the on switch and the tabs

Turning on Policy author asks you to confirm, because a policy author loses every tool: the provider sandbox, its connector tools and the gateway's own tools. Turning it off restores them.

When the agent is also an evaluator, the confirmation warns This agent is also an evaluator. The agent keeps reviewing sessions. It can no longer raise alerts through its connector tools, such as posting to chat, opening a ticket or sending mail.

The Activity Tab​

The Activity tab lists every tool call the agent made, across all its connectors. Use it to see what an agent did, and how the gateway decided each call.

  • Time range. Choose 1h, 24h, 7d or 30d. The tab opens on 24h, and shows up to 100 calls.

  • Protocol calls. Select it to include the handshake calls an agent makes before it can call a tool.

  • Refresh. Click Refresh to load the latest calls.

Each row shows these columns.

ColumnWhat it shows
TimeWhen the call was made
Tool / methodThe tool called, or the protocol method for a handshake call
ConnectorThe connector the call went to
DecisionAllowed, Denied, Approval or Error with its status code
OwnerThe person the call is attributed to

Click a row to open the call's details: its decision, status code and duration, the agent, the owner and a summary of its arguments.

Who sees which calls depends on your role:

  • Everyone's calls. The agent's owner, and anyone whose role reaches all agents.

  • Only your own calls. A person assigned to an agent they do not own, whose role reaches only their own agents.

Turning a Cloud Agent Off​

Turn a cloud agent off from the Agents page, from its details, or with the Enabled switch in its page header. The gateway refuses its next call, and its work at the provider ends too:

  • Anthropic sessions are interrupted, then archived.

  • AWS Bedrock AgentCore runtime sessions are stopped in AWS.

  • Messages are refused, in its existing conversations and in a new chat.

  • An automation run in progress ends. See How Runs Behave.

The agent's definition at the provider is untouched. When you turn it back on, people start new conversations with it. A conversation that was running when it was turned off cannot be continued.

For the steps, what is kept, and who can turn an agent off and on, see Turning Off an Agent.

Lifecycle Stages​

Every agent also has a lifecycle stage, separate from whether it is switched on. That includes cloud agents, AWS Bedrock agents and workload agents.

The stage records where the agent is in its life, and decides whether access reviews include it.

Three lifecycle stages. Production: in use, every new agent starts here, can be switched on, reviewed on the Production schedule. Retain data only: switched off, records kept, cannot be switched on, reviewed on its own schedule. Retired: switched off and out of use, hidden from the list, cannot be switched on, not reviewed. Leaving Production switches the agent off. Returning to Production leaves it off until you turn it on

The following table summarizes each stage.

StageWhat it meansReviewed
ProductionIn use. Every new agent starts hereYes, on the Production agents schedule
Retain data onlySwitched off. Its records are keptYes, on its own schedule
RetiredSwitched off and out of useNo

To move an agent to another stage:

  1. On the agent's detail page, click Change stage.
  2. Choose the stage. Each option describes its effect.
  3. Enter a Reason, up to 500 characters. A reason is required, and AgentPass records it with your name.
  4. Click Change stage. When the agent is leaving Production, the dialog warns This switches the agent off on its next request. The button then reads Yes, move and turn off.

Changing the stage needs permission to edit the agent. Stage changes interact with the Enabled switch:

  • Leaving Production switches the agent off. Its next request is refused.

  • Only a Production agent can be switched on. In any other stage, the Enabled switch is unavailable until you move the agent back to Production.

  • Returning to Production does not switch the agent on. Turn it on separately when you are ready.

An agent outside Production shows its stage in two places:

  • On the Agents page, as its status.

  • On its own page, as a tag. Its page also shows who moved it and when, for example Retired by the person's address and 3h ago.

Retired agents are hidden from the list. Turn on Show retired to see them.

The audit trail records every stage change with the old stage, the new stage and the reason.

An access review's Remove all access switches an agent off, but never changes its stage.

Every agent also has a lifecycle stage: Production, Retain data only or Retired. The stage decides whether access reviews include the agent, and only a Production agent can be turned on. To change it, click Change stage on the agent's page. See Lifecycle Stages.

Assigning an Agent to People​

An agent is used by the people and groups assigned to it. Assignment controls who can start sessions with the agent and whose automations may run it. The agent's audit trail records every grant and revocation.

When an assignment is a person's last path to the agent, removing them on the Assignments tab revokes their credentials for that agent. It also interrupts their sessions on it. A person who still belongs to an assigned group keeps access.

Shared identity needs an explicit acknowledgement

An AWS Bedrock agent without per-user credential isolation runs its tool calls as one shared identity, whoever is chatting with it.

When you assign such an agent to a group, or to more than one person, AgentPass asks you to acknowledge that. The audit trail records the acknowledgement.

Governance: What the Gateway Sees​

A managed cloud agent's tools are gateway connectors: Model Context Protocol (MCP) servers and REST API connectors. When the agent calls one, the call reaches AgentPass with a gateway-issued credential that identifies the agent.

The call then goes through the same pipeline as every other request:

  • Policies allow the call, block it, or require approval. See Policies.

  • Approvals follow the standard human-in-the-loop flow. A blocked agent learns how to request approval, and continues once it is granted.

  • The Request Log and audit trail record every call, attributed to the agent.

The agent's list of connectors bounds which credentials it is issued. An agent never receives a credential for a connector outside its list.

Provider-side tools are outside the gateway

An Anthropic cloud agent can also carry the provider's built-in sandbox tools: shell, file operations and web fetch. Those run inside Anthropic's environment and never pass through the gateway.

No policy applies to them, and no audit row is written. The gateway's guarantees cover the agent's connector tools. See Anthropic Cloud Agents for what this means in practice.

Who Can Do What​

Access to cloud agents follows permissions. See Permissions by Role.

TaskPermissionOut of the box
See cloud agentsAgents: View, Cloud Agents: ViewAdmin, Operator, Security analyst and Auditor, for every agent. Supervisor, for the agents they own or are assigned to
Create an Anthropic agent, edit its configuration and re-sync itCloud Agents: ManageAdmin, for every agent. Operator and Supervisor, for the agents they created
Import agents from a providerAgents: SyncAdmin and Operator
Change the stage, tag as evaluator or policy author, and assign peopleAgents: EditAdmin and Operator
Turn an agent off and on, and manage its automationsAgents: ToggleAdmin, Operator and Security analyst, for every agent. Supervisor, for their own. See Who Can Turn an Agent Off and On