AISense is the artificial intelligence (AI) powered capability of Automation 360 that helps you identify objects from an image or an application with a complex user interface (UI) and make automation in all environments faster and more accurate.

AISense is suitable when object-based automation fails or is not efficient for automating tasks on applications that are accessed remotely, in a Citrix environment, and legacy applications.

Some of the issues that affect the accuracy of an automation task in a remote environment are as follows:
  • In a Citrix environment, the automation platform receives an image of the application and does not have access to the actual UI elements.
  • Screen resolution and scaling might not be the same on the host and client machines.
  • The position of a UI element might change for web applications due to a different resolution on the Bot Runner machine.

AISense uses computer vision to intelligently create dynamic linking between objects by determining their composition to deliver change-resilient automation. AISense enables you to accurately automate applications even when labels and text change their position.

Important:
  • Bots will fail if they contain actions from Recorder package versions 2.0.9-20201105-164103 or later and the AISense package. You must delete the AISense actions and recapture the objects using the integrated recorder icon. An integrated Recorder
  • AISense Recorder supports the following languages: English, Simplified Chinese, Korean, Brazilian-Portuguese, Japanese, and Russian. When you record an application, ensure that the device locale is set to the same language as that of the application, regardless of operation system and keyboard layout. If the user interface (UI) of the application is a combination of English and another language, set the device locale to the other language. For example, if the UI is a combination of English and Russian, set the device locale to Russian.
    Note: Even if the device locale is set to a language other than English, you can continue to automate applications that have an English UI without changing the device locale to English.

Recommendation: On any application, regardless of the language of the application, when you use the Get text action to retrieve text from a specified area, if the retrieved text is not accurate, we recommend that you perform one of the following actions and then record again:
  • Increase the font size.
  • Decrease the screen resolution.
  • Zoom in to capture the text correctly.