- Overview
- UI Automation
- Applications and technologies automated with UI Automation
- Project compatibility
- UI-ANA-016 - Pull Open Browser URL
- UI-ANA-017 - ContinueOnError True
- UI-ANA-018 - List OCR/Image Activities
- UI-DBP-006 - Container Usage
- UI-DBP-013 - Excel Automation Misuse
- UI-DBP-030 - Forbidden Variables Usage In Selectors
- UI-DBP-031 - Activity verification
- UI-PRR-001 - Simulate Click
- UI-PRR-002 - Simulate Type
- UI-PRR-003 - Open Application Misuse
- UI-PRR-004 - Hardcoded Delays
- UI-REL-001 - Large Idx in Selectors
- UI-SEC-004 - Selector Email Data
- UI-SEC-010 - App/Url Restrictions
- UI-USG-011 - Non Allowed Attributes
- UX-SEC-010 - App/Url Restrictions
- UX-DBP-029 - Insecure Password Use
- UI-PST-001 - Audit Log Level in Project Settings
- UiPath Browser Migration Tool
- Clipping region
- Computer Vision Recorder
- Remote UI Automation design (Live authoring)
- Activities index
- Activate
- Anchor Base
- Attach Browser
- Attach Window
- Block User Input
- Callout
- Check
- Click
- Click Image
- Click Image Trigger
- Click OCR Text
- Click Text
- Click Trigger
- Close Application
- Close Tab
- Close Window
- Context Aware Anchor
- Copy Selected Text
- Element Attribute Change Trigger
- Element Exists
- Element Scope
- Element State Change Trigger
- Export UI Tree
- Extract Structured Data
- Find Children
- Find Element
- Find Image
- Find Image Matches
- Find OCR Text Position
- Find Relative Element
- Find Text Position
- Get Active Window
- Get Ancestor
- Get Attribute
- Get Event Info
- Get From Clipboard
- Get Full Text
- Get OCR Text
- Get Password
- Get Position
- Get Source Element
- Get Text
- Get Visible Text
- Go Back
- Go Forward
- Go Home
- Google Cloud Vision OCR
- Hide Window
- Highlight
- Hotkey Trigger
- Hover
- Hover Image
- Hover OCR Text
- Hover Text
- Image Exists
- Indicate On Screen
- Inject .NET Code
- Inject Js Script
- Invoke ActiveX Method
- Key Press Trigger
- Load Image
- Maximize Window
- Microsoft Azure Computer Vision OCR
- Microsoft OCR
- Microsoft Project Oxford Online OCR
- Minimize Window
- Monitor Events
- Mouse Trigger
- Move Window
- Navigate To
- OCR Text Exists
- On Element Appear
- On Element Vanish
- On Image Appear
- On Image Vanish
- Open Application
- Open Browser
- Refresh Browser
- Replay User Event
- Restore Window
- Save Image
- Select Item
- Select Multiple Items
- Send Hotkey
- Set Clipping Region
- Set Focus
- Set Text
- Set To Clipboard
- Set Web Attribute
- Show Window
- Start Process
- System Trigger
- Take Screenshot
- Tesseract OCR
- Text Exists
- Tooltip
- Type Into
- Type Secure Text
- Use Foreground
- Wait Attribute
- Wait Element Vanish
- Wait Image Vanish
- Accessibility Check
- Application Event Trigger
- Block User Input
- Check/Uncheck
- Check App State
- Check Element
- Click
- Click Event Trigger
- Drag and Drop
- Element Scope
- Extract Table Data
- Find Elements
- For Each UI Element
- Get Browser Data
- Get Clipboard
- Get Text
- Get URL
- Go to URL
- Hide Status Window
- Highlight
- Hover
- Inject Js Script
- Keyboard Shortcuts
- Keypress Event Trigger
- Mouse Scroll
- Navigate Browser
- Save Image
- Select Item
- Set Browser Data
- Set Clipboard
- Set CV Server
- Set Runtime Browser
- Set Focus
- Set Project Setting
- Set Text
- Show Status Message
- Show Status Window
- Take Screenshot
- Type Into
- Unblock User Input
- Window Operation
- Perform browser search and retrieve results using UI Automation APIs
- Web Browsing
- Find Images
- Click Images
- Trigger and Monitor Events
- Create and Override Files
- HTML Pages: Extract and Manipulate Information
- Window Manipulation
- Automated List Selection
- Find and Manipulate Window Elements
- Manage Text Automation
- Load and Process Images
- Manage Mouse Activated Actions
- Automate Application Runtime
- Automated Run of a Local Application
- Browser Navigation
- Web Automation
- Trigger Scope Example
- Enable UI Automation support in DevExpress
- Computer Vision Local Server
- Mobile Automation
- Release notes
- About the mobile device automation architecture
- Project compatibility
- Get Log Types
- Get Logs
- Get Page Source
- Get Device Orientation
- Get Session Identifier
- Install App
- Manage Current App
- Manage Other App
- Open DeepLink
- Open URL
- Mobile Device Connection
- Directional Swipe
- Draw Pattern
- Positional Swipe
- Press Hardware Button
- Set Device Orientation
- Take Screenshot
- Take Screenshot Part
- Element Exists
- Execute Command
- Get Attribute
- Get Selected Item
- Get Text
- Set Selected Item
- Set Text
- Swipe
- Tap
- Type Text
- Terminal
- Release notes
- About the Terminal activity package
- Project compatibility
- Best practices
- Find Text
- Get Color at Position
- Get Cursor Position
- Get Field
- Get Field at Position
- Get Screen Area
- Get Text
- Get Text at Position
- Move Cursor
- Move Cursor to Text
- Send Control Key
- Send Keys
- Send Keys Secure
- Set Field
- Set Field at Position
- Terminal Session
- Wait Field Text
- Wait Screen Ready
- Wait Screen Text
- Wait Text at Position
- Terminal coded automation APIs
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:
- Use variables
- Attach files
- Add image from screen (inline with the text)
- View last execution trace. For more details, refer to Running and inspecting the execution results
-
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
Stringoutput. - Trace files - The trace files generated by the current ScreenPlay activity. Trace files are generated according to the ScreenPlay project setting.