Create and manage Model connections

Connect to a curated list of foundational models from hyperscaler vendors such as Amazon Bedrock, Google Vertex AI, Azure OpenAI, OpenAI and others to integrate the power of generative AI into your automations.

The Automation Admin creates and tests Model connections by connecting to foundational models and makes these connections available to the Pro Developers, who would connect to these when creating AI Skills. The Model connections are used in Prompt Templates to send prompts and receive responses from the models.

Additionally, the Automation Admin creates custom roles and assigns these Model connections to the custom roles. These custom roles are then assigned to users who would be able to access the Model connections.

Follow these steps to create a Model connection.

Prerequisites

The Automation Admin requires these roles and permissions to create and manage Model connections for their business organization.
  • Role: AAE_Basic, Automation Admin custom role
  • Permission: Attended Bot Runner
  • Settings: AI Data Management must be enabled by the Automation Admin and the check box selected for Allow users to disable logs on AI Skills. Allow users with the Bot Creator license to disable data logging when using AI Skills.

See Roles and permissions for AI Tools for the Automation Admin custom role permissions.

Other requirements:
  • If you want to store authentication details in a credential vault, have that information handy. See Secure credential store through Credential Vault.
  • To test a Model connection, you must be connected to a Bot Agent 22.60.10 and later. As part of the test, you would have to run the bot on your desktop. Hence ensure the Bot Agent is configured to your user. For this task, if you have to switch connection to a different Control Room, see: Switch device registration between Control Room instances.
  • You would need access to the Recorder package and the AI Skills package to test the connection successfully. A test Prompt would be executed to test the Model connection.

Procedure

  1. In your Control Room environment, navigate to AI > Model Connections and click Create model connection.
  2. In the Create model connection screen you would configure these Connection settings:
    Create Model connections
    1. Model connection name: Provide a name for easy identification of the Model connection.
    2. Description (optional): Add a meaningful short description defining the connection.
    3. Choose a vendor: Choose a foundational model vendor from the supported list of vendors such as Amazon Bedrock, Google Vertex AI, Azure OpenAI, or OpenAI.
    4. Choose a type: After you select a model from the drop-down list, the Choose a type field displays. Select Standard from the drop-down list.
    5. Choose a model: Choose a model from the drop-down list. The list displays relevant models as per your vendor selection.
      For a complete list of supported models for each foundational model vendor, see General FAQs.
    6. Click Next to proceed to the Authentication details section.
  3. In the Authentication details section, configure the parameter settings. which vary based on the model you chose when defining the Model connection.
    Note: For authentication details for each model, see Authenticate Model connections.
  4. After setting up the authentication details, Confirm and click Next to proceed to the Test connection section to test the Model connection.
  5. Click Test connection to make sure all connection details have been defined correctly and check if the connection is working.
    This is a desktop operation using a Bot Agent. Use Bot Agent 22.60.10 and later for successful testing.
    • If the connection works as expected, the system will process the request and you will get a system generated success message.
    • If the connection does not work as expected, you will get a system-generated message stating the reason for the connection failure. For example, if you have not downloaded the supported foundational model package to your workspace, you would get an error message. You would have to download the package and then retest the Model connection.
    • If the testing a Model connection is unsuccessful or if you leave the task incomplete, the Model connection will not get saved and you will have to restart the process of creating the Model connection.
  6. Click Next to proceed to the Invite roles section to begin assigning custom roles to users.
    The Automation Admin would create custom roles and assign the Model connections to the role, which can then be assigned to users. Only users assigned to this custom role can use this Model connection.

    Assign custom role to users

  7. Assign access to the Pro Developer via custom role (using RBAC), for using this Model connection to create an AI Skill.
  8. Click Create model connection to complete creating the Model connection.
    After successfully creating the Model connection, the Pro Developer would use it to create an AI Skill

    See: Create AI Skills.

  9. You will get a system-generated success message stating that your Model connection was created. You will get directed to the Model connections screen displaying a list of Model connections.
    Model connection is a success
  10. You can View connection, Edit connection, Change status or Delete each connection by clicking on the ellipsis next to them.
    Model connection actions
    Actions Function
    View connection

    Connection details gives you a summary-view of the model.

    General details displays when the connection was last modified and by whom.

    The Automation Admin can edit the Model connection from this view.
    Change status
    A Model connection gets created with the Available status. The Automation Admin can change the status of a Model connection to any of the following:
    • Available: Model connection can be used to create new AI Skills and run existing ones.
    • Limited Access: Model connection is available for running existing AI Skills, but you cannot add this to new ones.
    • Disabled: New Prompt Templates cannot be created using these Model connections. All existing automation executions using these Model connections will fail.
    Edit connection Lets you edit the Model connection details.
    The Edit button is enabled for the Automation Admin only.
    Note: Users, such as the Pro Developer, and Citizen Developer, with the Model connections > View Model connections permission, would be able to see details of the Model connection but not edit it.
    Delete

    Clicking on Delete displays a message asking for your confirmation and then deletes the Model connection. You will get a message confirming the deletion.

    If you delete a Model connection, all AI Skills referencing the deleted Model connection will fail to connect to the foundational model, which would cause all automations, using the Prompt Templates to fail execution.

    The Delete button is enabled for the Automation Admin only.
    Note: Users, such as the Pro Developer, and Citizen Developer, with the Model connections > View Model connections permission, would be able to see details of the Model connection but not delete it.

Next steps

After creating and testing the Model connection, you would assign it to the Pro Developers, who would use this connection to create AI Skills. See Create AI Skills
Note:
When you create, test, edit or delete a Model connection, the success or failure details along with the model responses are captured as logs and can be viewed in these navigation screens:
  • Administration > AI governance > AI Prompt log
  • Administration > AI governance > Event log
  • Administration > Audit log
See AI governance.

As the next step in your sequence of tasks, go to Create AI Skills to create an AI Skill and connect to a Model connection and then use it in an automation.