Multi-device visual correlation interaction includes displaying, by a first device, a user interface representation of a user interface displayed by a second device, the user interface representation containing one or more element representations, each element representation corresponding to an element contained within the user interface displayed by the second device; receiving from a user of the first device, a selection of a particular element representation of the user interface representation, the particular element representation corresponding to a particular element contained within the user interface; transmitting to the second device, by the first device, a contextual information request corresponding to the selection; in response to transmitting the contextual information request, receiving from the second device, by the first device, contextual information corresponding to the selection; and generating based on the contextual information, by the first device, a contextual list of actions associated with the particular element.