Installing ScreenPlay

The ScreenPlay installation procedure supports the following deployment options:

• The out-of-the-box (OOB) deployment option - gives you free access to a list of available models:
  • UiPath (with Gemini 2.5 Flash)
  • UiPath (with GPT - 4.1)
  • UiPath (with GPT 4.1 mini)
  • UiPath (with GPT - 5)
  • UiPath (with GPT - 5 mini)
  • OpenAI Operator
  • Anthropic - Computer Use

• The bring-your-own-model (BYOM) deployment option - allows you to use your own existing subscription to power ScreenPlay.

  With BYOM deployment, there are no imposed limits on how much you can use the service.

  To perform this installation, you need to have your own subscription for one of the following services:

  • Azure Open AI
  • Open AI
  • Amazon Bedrock (Anthropic Computer Use)
  • Google Vertex

  • Open AI V1 Compliant LLM – Use this option to connect to any LLM provider whose API follows the OpenAI V1 standard.

    For details, refer to the OpenAI V1 Compliant LLM connector documentation.

Studio - ScreenPlay setup

Prerequisites

ScreenPlay is supported by any version of UiPath Studio. However, we strongly recommend using Studio 2025.10 in order to benefit from the following capabilities:

• You can easily edit prompts in a modern editor.
• You can insert and manage variables, and images inline with text.

Note: Older Studio versions still support ScreenPlay but use a more basic and less flexible editor. In older versions, inline images are not supported, and you must write variables using the {{variable}} syntax.

To configure ScreenPlay via Studio, take the following steps:

1. Open UiPath Studio, and create a new project.
2. Navigate to cloud.uipath.com and ensure you are connected to your Automation Cloud account.

3. Add the latest UIAutomation package, 2025.10.20 or newer, by navigating to Manage Packages, then select Settings.

   In the Default package sources section, ensure you enable the Official package.

4. In the project canvas, select the Add Activity icon to search and add the ScreenPlay activity.

5. In the ScreenPlay activity, add a prompt in the Task field.

   Additionally, you can change the default LAM from the Model drop-down, and tailor other properties, if needed.

Studio Web - ScreenPlay setup

To configure ScreenPlay via Studio Web, take the following steps:

1. Navigate to https://cloud.uipath.com, and log in to your account.
2. Navigate to Studio, select Create New, and then select RPA Workflow.
3. Select the Add activity icon to search and add the ScreenPlay activity to the project canvas.

4. In the ScreenPlay activity Properties panel, add a prompt in the Task field.

   Additionally, you can change the default LAM from the Model drop-down, and tailor other properties, if needed.

   
   

   

   
   

Bring-your-own-model setup

To use your own subscriptions, take the following configuration steps via LLM configurations in AI Trust Layer:

1. In Automation Cloud™, navigate to Admin.
2. Select AI Trust Layer, then select the LLM configurations tab.
3. Select a tenant from the Tenant drop-down, and then select Add configuration.
4. In the Add configuration panel, take the following steps:
   1. Select UI Automation from the Product drop-down.
   2. Select ScreenPlay from the Feature drop-down.
   3. Select Replace UiPath LLM subscription from the Configuration mode drop-down.
   4. Select the subscription you have and want to use from the LLM drop-down.
   5. In the Configure customer managed connection section, select a folder from the Folder drop-down, and then select a connector from the Connector drop-down.
   6. Select Add new connection. A new tab opens, prompting you to provide information to connect UiPath to your selected connector. Populate the necessary fields, then select Test in the Add configuration panel.
   7. Select Save.

For more information, refer to Configuring LLMs.

Important precautions

For a safe use of ScreenPlay, you must take the following important precautions:

• Current state-of-the-art LAMs are quite limited, therefore it is better to use multiple granular ScreenPlay activities, each handling one or two actions with a few target UI elements, rather than a single end-to-end automation instance attempting a complex task.