Skip to main content

Deploy agents

Configure agent settings and deploy them to your clusters. Select the agents, target cluster, and passport profile.

Before you begin

Select and deploy AI agents

Choose the target cluster and passport profile for the selected agents. The cluster determines where the agents are deployed, while the passport profile provides their identity and associated security policies.

  1. In the AI Trust manage main menu, select Agent Trust > Agents > Agent images.

  2. Select agents from the list and select Deploy image.

    Or, select Add registry to fetch agents from a specific agent registry.

  3. Select the Cluster to deploy the agents and a Passport profile. to define capabilities, and security constraints.

  4. Configure the following for each of the selected agents:

    1. Specify the No. of replicas, number of instances of the agent workload to run concurrently.

      Multiple replicas can improve availability and provide capacity for concurrent requests.

    2. Select the agent image Version or image version to deploy. This determines the specific agent configuration that will run.

    3. Provide a custom Agent name (optional) to identify the deployed agent. If left blank, a system-generated name may be assigned.

    4. Define the Exposure: setting to fine how an agent can be accessed:

      1. Select the Cluster to make the agent accessible within the cluster or connected internal environment.

        (OR)

        VPC to expose the agent to resources within the configured virtual private cloud.

      2. Specify the primary network Port on which the agent listens for incoming requests.

      3. Specify Additional ports the agent requires for communication.

      4. Define Allowed sources to access the agent.

        注意

        Enter comma-separated IPv4 CIDRs or AWS security group IDs. Examples: 10.0.0.0/16, sg-12345678.

    5. Specify the Managed policy ARNs to attach predefined permissions to the agent.

    6. Define an Inline policy (JSON) specify the permissions, rules, or restrictions that apply to the agent. The policy is stored and managed as part of the agent configuration.

    7. Specify the Project roles, the permissions granted to access and manage resources in the selected Google Cloud project.

  5. After configuring all the agents, select Deploy selected.

    You can view the deployment status and progress. Once the agenta are deployed successfully, you can apply recommended security policies to protect your AI agents.

本节内容如下: