Abstract: In some embodiments, a natural language understanding (NLU) hypothesis may be determined for a natural language input to a device and a first component may be used to obtain first visual content corresponding to a first skill associated with the first NLU hypothesis. A second component may also be used to obtain second visual content corresponding to a second skill. The device may be caused to output a first graphical user interface (GUI) element including the first visual content and a second GUI element including the second visual content. In response to a subsequent input to the device corresponding to the second GUI element, the device may be caused to output content corresponding to the second skill.