A computing system generates an extended reality environment for an end user. The extended reality environment includes a plurality of tasks and a plurality of goals to be achieved by the end user. The computing system receives input data from an extended reality system associated with the end user. The computing system updates a progress of the end user through the plurality of tasks and the plurality of goals based on the input data. The computing system receives a voice command from the end user. The voice command corresponds to a statement uttered by the end user within the extended reality environment. The computing system processes the voice command to generate a response to the voice command. The computing system causes the response to appear within the extended reality environment as an audible, visual or haptic feedback response to the voice command.