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.
AgentPass supports three providers, and each reaches AgentPass differently.
| Provider | Where the agent runs | How it gets into AgentPass |
|---|---|---|
| Anthropic | Anthropic's Managed Agents platform | You create it in AgentPass from a template, a model, a prompt and tools. AgentPass provisions it on Anthropic. See Anthropic Cloud Agents |
| AWS Bedrock AgentCore | AgentCore in your own AWS account | Your team builds it in AWS. AgentPass imports it through a connector, then invokes and governs it. See AWS Bedrock AgentCore Agents |
| Microsoft 365 Copilot | Microsoft's cloud | You 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 type | How it arrives | Where to start |
|---|---|---|
| Anthropic, new agent | Create: New agent → New cloud agent | Set Up an Anthropic Cloud Agent |
| Anthropic, built in the Anthropic console | Import: Import agents, then sync the Anthropic Managed Agents connector | Set Up an Anthropic Cloud Agent |
| AWS Bedrock AgentCore | Import: create the connector, then sync it from Import agents | Set Up an AWS Bedrock AgentCore Agent |
| Microsoft 365 Copilot | Connect: register Copilot Studio agents on the connector | Set 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.
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.
| Tab | What it holds |
|---|---|
| Overview | Provider, 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 |
| Chat | A direct conversation with the agent. Use it to test a new agent before anyone else does. Anthropic and AWS Bedrock agents only |
| Automations | Runs on a schedule. Anthropic and AWS Bedrock agents only. See Automating Cloud Agents |
| Assignments | Which users and groups may use the agent. Not shown for workload agents |
| Activity | The agent's recent tool calls. See The Activity Tab |
| Credential | The workload agent's gateway credential. Workload agents only. See Managing Workload Agents |
| Tools | The 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:
-
Enabled turns the agent on and off. See Turning Off an Agent.
-
Evaluator lets the agent review coding sessions. See Session Watch.
-
Policy author lets it draft policies for you. See Choosing Who Drafts Your Policies.
-
Edit configuration, Re-sync and Remote config, for an Anthropic agent. See Keeping AgentPass and Anthropic in Step.
-
Change stage. See Lifecycle Stages.
-
The On switch, which reads Off while the agent is turned off. See Enabling and Disabling.
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.
| Column | What it shows |
|---|---|
| Time | When the call was made |
| Tool / method | The tool called, or the protocol method for a handshake call |
| Connector | The connector the call went to |
| Decision | Allowed, Denied, Approval or Error with its status code |
| Owner | The 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.
The following table summarizes each stage.
| Stage | What it means | Reviewed |
|---|---|---|
| Production | In use. Every new agent starts here | Yes, on the Production agents schedule |
| Retain data only | Switched off. Its records are kept | Yes, on its own schedule |
| Retired | Switched off and out of use | No |
To move an agent to another stage:
- On the agent's detail page, click Change stage.
- Choose the stage. Each option describes its effect.
- Enter a Reason, up to 500 characters. A reason is required, and AgentPass records it with your name.
- 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.
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.
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.
| Task | Permission | Out of the box |
|---|---|---|
| See cloud agents | Agents: View, Cloud Agents: View | Admin, 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 it | Cloud Agents: Manage | Admin, for every agent. Operator and Supervisor, for the agents they created |
| Import agents from a provider | Agents: Sync | Admin and Operator |
| Change the stage, tag as evaluator or policy author, and assign people | Agents: Edit | Admin and Operator |
| Turn an agent off and on, and manage its automations | Agents: Toggle | Admin, Operator and Security analyst, for every agent. Supervisor, for their own. See Who Can Turn an Agent Off and On |
Related
- Find an Agent — find, import, create and turn off every agent
- Anthropic Cloud Agents — create, configure and run an agent on Anthropic
- AWS Bedrock AgentCore Agents — import, govern and equip agents built in your AWS account
- Automating Cloud Agents — schedules and run history
- Running Agent Access Reviews — confirm on a schedule that each agent still needs its access