Managing an AI agent using the UI

You can create an AI agent by integrating workflows and Large Language Models (LLM) in a single platform. You can then communicate with the AI agent either using a chatbot interface in the UI or by running the AI. You can interact with the AI agent either from the AI Agents section in the UI or you can create tasks to run the agent.

Before you begin

You must have completed the following:
  • Obtained valid credentials to access the HCL Universal Orchestrator UI.
  • Created required workflows.
  • Obtained ADD access.
  • Obtained USE access on the AI agent.
  • Obtained USE access on the workflows that you want to add in the AI agent.
  • Configured the required AI models (LLM) in your HCL Universal Orchestrator environment. For more information, see Managing agent types in the AI agent.

About this task

You can create an AI agent to automate selected scenarios. You can integrate workflows and specific AI models to create an AI agent that acts as a hub for information that can be accessed on demand. The AI agent facilitates access to organized information, permitting AI models to automate tasks or provide rapid responses from the information center.

Procedure

  1. Log in to the UI using valid user credentials.
  2. Select the Design tab from the home page.
  3. In the Graphical Designer page, select the Blocks tab.
  4. Drag and drop an AI agent instance from the Blocks tab to the canvas.
    The AI Agent panel is displayed. Enter valid details for the mandatory fields and you can fill in optional fields to customize the AI agent behavior.
    Table 1. Mandatory fields
    Option Description
    General information
    Folder

    Specify a folder to save the AI agent definition. The default value is the root folder (/). The name must start with a letter, and can contain alphanumeric characters, dashes, and underscores. The name of the folder cannot contain spaces.
    Name

    Specify a name for the AI agent. The name must start with a letter, and can contain alphanumeric characters, dashes, and underscores. The name cannot contain spaces.
    Agent type
    You can specify the AI model type that you want to utilize to assist the operations managed by the AI agent. You can select any one of the following:
    • Basic
      The AI models (LLM) are configured directly with the agent. You can configure any AI models provided by the foundational model platforms or AI/Machine learning cloud platforms. You must have configured those AI models in your environment by configuring the values.yaml file. For more information, see Managing agent types in the AI agent. If you select this option, you must also complete the following field.
      Model
      All the AI models configured in your environment (the AI models configured in the values.yaml file) are displayed and you can select anyone from the drop-down list.
      Example: gpt-4, amazon.nova-micro-v1:0,anthropic.claude-3-haiku-20240307-, gemini-2.0-flash, gemini-2.5-flash.
      Note: v2.1.6+To integrate the latest Gemini 3.x models with the AI agents, you must upgrade your environment to HCL Universal Orchestrator 2.1.6.
    • External (MCP)
      Select this option, if you want to integrate the AI agent with external MCP platforms. While creating the AI agent a unique URL with the agent ID (MCP server URL) is auto generated. You can use this URL to connect the AI agent with any external MCP server. You can then communicate with the MCP server using its access points and it provides responses powered by the integrated AI models. For more information, see Course of action if the agent type is External MCP.
    • Agentic AI builder
      The advanced and customized AI agents that utilize multiple AI models. After creating the AI agent a unique URL with the agent ID (MCP server URL) is auto generated. Use this URL to connect the AI agent with the Agentic AI Builder. For more information, see UnO Agentic AI Builder. You must complete the following field if you select this option:
      • Agentic AI Builder Agent Name
        Select the agent package name from the drop-down list. You must have updated the values.yaml file to set the value of the attribute enableAgenticAIBuilder to true. Then all the agents deployed from the Agentic AI builder appear in the drop-down list.

        v2.1.5+This feature is available in HCL Universal Orchestrator multitenant environments; each tenant manages their own agents independently.
    Workflows
    workflows Add all the required workflows to the AI agent. Each workflow must define its service name, description, and variables so the agent knows what input to pass, and its output properties so the agent knows what result to expect. Publishing the workflow on the Self-Service Catalog is not required; adding it to this list is enough. For details, see Creating workflows as a service using Orchestration CLI and Output properties and data transfer between workflows.
    Important: Describe each service variable clearly. As the number of input variables grows, an accurate description of each one becomes critical to reduce hallucinations by the model.
    • To add an existing workflow, click Add new +, and then click in the Workflow field. Select an existing workflow from the drop-down list or else, navigate to Assets → workflows, and then drag and drop an existing workflow from the list.
    • To add a new workflow, click the Blocks tab, and then drag and drop a workflow.
    Table 2. Optional fields
    Options Description
    General information
    Display name

    Specify a name to identify the AI agent in the AI Agents section. You must add this attribute, only if you want to create an AI agent with a chatbot interface. The name must start with a letter or a number, and can contain alphanumeric characters, dashes, and underscores. The name cannot contain spaces. If no details are added, then the name specified for the Name field is used to identify the AI agent.
    Description

    Provide a description for the AI agent. You can add information about the workflows that are added in the agent, details like what the workflows do and output that it produces. This detail helps the Agent type to manage the AI agent more efficiently and effectively.
    Published as Chatbot

    If you want to interact with the AI agent in a chatbot interface, set the option to on. Enabling this option creates a chatbot interface for the AI agent in the AI Agents section in the UI. If this option is not set, you must run tasks to communicate with the AI agent.
    Specific attributes for basic agent type
    The following are specific attributes to customize the basic agent type.
    Table 3. Optional fields
    Options Description
    General information
    Role

    You can specify the role of the agent in free-form text.
    Icon You can select any icon from the drop-down list and the same is displayed for the agent along with the name in the AI Agents section. You can utilize this option, if you decide to publish the AI agent with a chatbot interface.
    Temperature
    It controls the randomness and creativity of the output or generated text provided by the AI agent. You can select any value between 0 and 2.0. A value close to 0 gives more generic and common phrasing. A value close to 2.0 gives a more unique phrasing.
    Note: For the basic agent type, the available range depends on the specific model selected. Ensure that the temperature value you provide is supported by the selected AI model.
    Instructions

    You can provide instructions to the AI agent in free-form text. The content you add here plays a vital role in the performance of AI agent. Based on the instructions provided here, the agent manages the workflows included in the AI agent to provide the output. You can specify all the operations and tasks the agent must perform. You do not need to reference a specific workflow here. If you must enforce the use of a particular workflow, reference its service name, not the workflow name.
    Guardrails

    You can specify all the operations the AI agent should avoid. Specify all the restrictions and limitations you want to put on managing the data transfer.
    Top-P

    Top-p, or nucleus sampling, is the attribute that controls the diversity of the generated text. It selects the smallest set of most probable next words whose cumulative probability exceeds a specified threshold (between 0 and 1). The model then samples the next word only from this "nucleus" set. A higher value leads to more diverse and creative outputs, while a lower value results in more focused and predictable text.
    v2.1.7+Verbose Errors Controls whether the output displays detailed diagnostic data when an error occurs. When set to on, this setting provides detailed error descriptions to help with troubleshooting.
    Note: v2.1.7+For some AI models you cannot set both the Temperature and Top-p parameters. You must specify only one parameter to create the agent.

  5. Click Deploy.

Results

You have successfully created an AI agent.

What to do next

You can interact with the agent either from the AI Agents section in the UI or you can create tasks to run the agent.