A mobile phone robot is able to perform multi-touch operations on a mobile phone. A fastener holds a mobile phone stationary relative to the mobile phone robot. A first robot arm subsystem controls location and timing of contact of a first stylus tip with a touchscreen of the mobile phone. A second robot arm subsystem controls location and timing of contact of a stylus tip with a touchscreen of the mobile phone. Screen mirroring technology is used to capture images displayed by the mobile phone. Control circuitry controls the first robot arm subsystem and the second robot arm subsystem. The control circuitry processes the images captured by the screen mirroring technology to detect text displayed within the image and to detect layout of the image.