agents
latest
false
  • Getting started
    • About agents
    • Agents workspaces
    • Governance
    • Data residency and supported models
    • Limitations
  • Prerequisites
  • Building agents in Studio Web
    • Building an agent in Studio Web
    • Best practices
    • Prompts
    • Contexts
    • Escalations and Agent Memory
    • Evaluations
    • Traces
    • Agent score – Preview
  • Building agents in Agent Builder
    • Building an agent in Agent Builder
    • Prompts and arguments
    • Tools
    • Contexts
    • Escalations and Agent Memory
    • Evaluations
    • Traces
UiPath logo, featuring letters U and I in white

Agents user guide

Last updated Apr 30, 2025

Building an agent in Agent Builder

This section describes how to create an agent in Agent Builder.

To learn how to create an Agent in Studio Web, refer to Building agents in Studio Web.

  1. In UiPath® Automation CloudTM, select Agents from the left-hand navigation bar.
    The Agents workspace is displayed.
  2. You can create your own agent, import one from a JSON definition, or start from one of the available templates. For details, refer to Using prebuilt agents.
  3. To create an agent from scratch, select New agent.
  4. The Agents workspace includes three tabs: Design, Evaluations, and Traces.

    Use the Design tab to design and define the core elements of your agent. Once you define the input/output arguments, you can use this space to preview your agent runs.

    Use the Evaluations tab to create evaluations and store results. Evaluations objectively measure your agent's output and assess whether or not it is consistent with your objectives.

    Use the Traces tab to log and represent all design and evaluation time traces for this agent. This is where you can see all the agent runs and the details of the run.

  5. First, select the large language model you want to use with your agent. Models are provisioned through UiPath AI Trust Layer.
    1. To configure model settings, select the settings icon next to the Model field. Here you can configure the Temperature and Max. tokens per response fields.
      • The Temperature determines the creativity factor of the LLM generation. You can set a value between 0 (Precise) and 2 (Creative).
      • Max. tokens per response refers to the maximum number of tokens to generate with the agent's response.
  6. In the General tab, give your agent a unique name and description.

    The name and description of the agent must offer details regarding the purpose of the agent in simple language. The description is used to help identify the agent in Studio.

  7. In the Prompt tab, add a well-structured system prompt and a user prompt to give your agent instructions for what it should do, and constraints it should follow.
  8. Select Arguments to access the Arguments window, where you can configure the input and output arguments used in your prompt.
  9. In the Tools tab, add any tools your agent can use during execution. These can be a set of Integration Service activities and published processes to which you have access.

    Each tool must have a detailed description that helps inform the agent how and when to use this tool.

  10. Use the Contexts tab to add any necessary context.

    Context Grounding indexes give an agent access to permissioned knowledge bases. This helps ground agent actions or answers in your business data.

  11. Use the Escalations tab to add a human in the loop and enable Agent Memory.

    Adding an escalation allows your agent to involve a human to review, approve, or update output as it is running.

  12. In the Playground window, provide input for a test run and select Run.

    You must test your agent to ensure it's operating as expected.

  13. Next, go to the Evaluations tab to review and measure your agent.

    An evaluation is a pair between an input and an assertion made on the output, and can be used to grade your agent during an end-to-end run.

  14. After you run the evaluations, use the Traces tab to review all the trace logs for your agent.
  15. Once you have tested, evaluated, and refined your agent, select Publish to publish it to Orchestrator as a process.
    • Select where to publish:
      • Orchestrator Personal Workspace Feed - The process is published to your personal workspace and will only be available to you. This is the default selection.
      • Orchestrator Tenant Processes Feed- The process is published to the global tenant feed and will be available to all users assigned to folders that use the tenant feed.
    • Select a version. A version is generated automatically starting with 1.0.0 when you first publish, and then incremented automatically every time you republish.
    Important: This step is necessary for the agent to be available in the Run Job activity.

    Select Export to view and package the agent definition as a JSON. You can then use this JSON extract to import the agent in a different organization.

  16. Finally, insert your agent into an automation using the Run Job activity in Studio. For details, refer to Running the agent.

Running the agent

Using agents as activities means you can incorporate them into workflows to handle parts of larger deterministic processes, have multiple agents act in series, and start agent execution based on triggers.

To incorporate your agent into a workflow, follow these steps:

  1. Publish your agent to Orchestrator.
  2. In Studio, use the Run Job activity to integrate your agent into a workflow.
  3. Whenever you make changes to your agent, republish the updated agent to Orchestrator and upgrade the corresponding process in Orchestrator.

    The Run Job activity always executes the version of the agent currently configured in Orchestrator. This ensures that your workflow consistently uses the most up-to-date version of your agent.

Refer to the System activities guide to learn how to configure and use the Run Job activity in your Studio workflows.

Note: Starting with UiPath.System.Activities version 25.4.2, the execution of agents and other Orchestrator jobs has been consolidated and improved under the Run Job activity. Existing workflows using the Run Agent activity continue to function without changes, ensuring a smooth transition. When adding new agent-running functionality to your workflows, the system automatically suggests and implements the Run Job activity, even if you search for Run Agent.

Using prebuilt agents

You can start your agentic journey with a set of prebuilt agents, available on the Agents landing page and in UiPath® Marketplace, via the Agent Catalog.

A prebuilt agent comes preconfigured for specific tasks. It requires a minimum configuration to be executable in Studio, and you can modify it and tailor it to your specific needs. A prebuilt agent has:

  • Predefined components - System prompts, activity tools with descriptions, starter evaluation sets.
    • Components are generic, not company or organization-specific.
    • Components are readily available in the agent when you access the Design tab in the Agents workspace. Some components (such as activities as tools) may need additional configuration, like creating the necessary connections in Integration Service.
  • Components that require additional configuration - Context Grounding indexes, automations and processes as tools, custom escalations, and all affiliated descriptions (instructions for the agent).
    • These components are organization and tenant-specific.
    • Components are also available in the UiPath Marketplace, packaged in prebuilt agents.

Using Agents from the UiPath Marketplace

To use a prebuilt agent from the UiPath Marketplace or an imported agent, you must first upload a set of necessary assets to your organization. These consist of processes, escalations, indexes, and connections.

When you import an agent from the Agents landing page, go to UiPath Marketplace and search for the same agent in the catalog to download the necessary assets.

A UiPath Marketplace agent listing can contain the following components:

  • The agent definition for importing the agent to the Agents workspace. You can also import prebuilt agents directly from the Agents home page.
  • Example documents for creating Context Grounding indexes for each prebuilt agent that uses Context Grounding. For details on creating an index, refer to Indexes.
  • A Solutions Management Assets package for deploying automations and custom escalations.
  • UiPath Studio and UiPath Apps components to customize what is contained in the Solution Management Assets.

To deploy an agent from the UiPath Marketplace, take the following steps:

  1. In UiPath Marketplace, choose an agent from the Agent Catalog and select Download & Open.

    The Downloading and Deploying an Agent window is displayed, with instructions on how to proceed next and a download link.

  2. Select Download Solutions Management Assets to retrieve the necessary package.
    A .zip file will be downloaded to your machine.
  3. Next, go to Solutions Management. You can access it through Automation Ops or directly in Orchestrator. For details, refer to Accessing the Solutions Management UI in the Solutions Management user guide.
  4. Upload the Solutions Management Assets package, as explained in Transporting a solution package.
  5. After configuring the Solutions Management Assets, go back to the Downloading and Deploying an Agent window and select Open in Agent Builder to get started with the prebuilt agent.
  • Running the agent
  • Using prebuilt agents
  • Using Agents from the UiPath Marketplace

Was this page helpful?

Get The Help You Need
Learning RPA - Automation Courses
UiPath Community Forum
Uipath Logo White
Trust and Security
© 2005-2025 UiPath. All rights reserved.