UiPath Documentation
activities
latest
false
UI Automation activities

ScreenPlay

ScreenPlay activity that screenPlay is UiPath®’s next-generation automation agent, designed to bring agentic behavior and cognitive capabilities to the desktop for Semantic Automation.

UiPath.Semantic.Activities.NUITask

Description​

ScreenPlay is UiPath®’s next-generation automation agent, designed to bring agentic behavior and cognitive capabilities to the desktop. ScreenPlay interacts with applications much like a human would—navigating interfaces, adapting to change, and handling complex tasks that were previously infeasible with traditional automation methods.

To learn more, refer to ScreenPlay.

This activity must be added inside a Use Application/Browser activity.

Project compatibility​

Windows | Cross-platform

Configuration​

  • Task - Prompt describing the UI task to be performed, with the ability to:

  • Model - Indicates the underlying LLM used by ScreenPlay for task execution planning and reasoning. The following options are available:

    Screen Agent (using Path Mini)

    • Basic model
    • Works on any type of application, including image-based interfaces
    • Uses a proprietary implementation based on the page's DOM and image understanding, using Path Mini for reasoning
    • Fast

    Screen Agent (using GPT-5.4)

    • Standard model - for complex tasks
    • Uses a proprietary implementation based on the page's DOM and image understanding, using GPT-5.4 for reasoning

    Screen Agent (using GPT-5.6 Luna)

    • Basic model - faster, cheaper
    • Uses a proprietary implementation based on the page's DOM and image understanding, using GPT-5.6 Luna for reasoning

    Screen Agent (using GPT-5.6 Terra)

    • Standard model - for complex tasks
    • Uses a proprietary implementation based on the page's DOM and image understanding, using GPT-5.6 Terra for reasoning

    Screen Agent (using GPT-5.6 Sol)

    • Standard model - for complex tasks
    • Uses a proprietary implementation based on the page's DOM and image understanding, using GPT-5.6 Sol for reasoning

    Screen Agent (using Gemini 3.8 Flash)

    • Basic model
    • Works best on browsers
    • Uses a proprietary implementation based on the page's DOM, using Gemini Flash for reasoning and image understanding
    • Moderately fast

    Default value is Screen Agent (using Path Mini).

  • Rate this activity - Good or Poor

Additional options​

Options​

  • Max number of steps - This is the maximum number of steps that ScreenPlay can take to achieve its goal. The property can be used as a basic guardrail to prevent infinite agentic loops.

  • Job attachment mode (.html trace) - Indicates when traces (.html) should be attached to the job. Trace files are generated according to the ScreenPlay project setting. Job attachment capabilities depend on the Orchestrator and Robot version. The following options are available:

    • On failure - Attach traces to the job only on failure.
    • Always - Always attach traces to the job.
    • Never - Never attach traces to the job.
  • Use DOM when available - Indicates whether DOM data will be used/sent to the LLM Model for applications where DOM can be extracted. DOM can be used only by UiPath LAM implementations.

    Disable if DOM-based targeting leads to incorrect element coordinates.

    Default value is True.

  • Disable variable security - Indicates whether the variable security should be disabled. Variable security ensures that prompt instructions can not be passed via variable values.

    The purpose of this feature is to prevent prompt injection attacks and is based on LLM, so if a "false positive" occurs, the user can disable it for each ScreenPlay activity. To conclude if it is a "false positive", the user can inspect the execution trace, system prompt, reasoning, and actions.

    Enable this option only if you need to pass prompt instructions via variable values or if a "false positive" result occurred.

    Default value is False.

Output​

  • Result - The result of the task, if any. For now we only support String output.
  • Trace files - The trace files generated by the current ScreenPlay activity. Trace files are generated according to the ScreenPlay project setting.
  • Description​
  • Project compatibility​
  • Configuration​
  • Additional options​
  • Options​
  • Output​

Was this page helpful?

Connect

Need help? Support(opens in new window)

Want to learn? UiPath Academy(opens in new window)

Have questions? UiPath Forum(opens in new window)

Stay updated