In one embodiment, in accordance with the present invention, a method for incorporating human comprehension and interaction with device-to-device communication between devices as they occur in a person's immediate surroundings. The method includes detecting that a user is present, wherein the user is detected by a first instance of a smart assistant software executing on the first device. The method further includes identifying an occurrence of a monitored event. The method further includes, in response to identifying the occurrence of the monitored event, determining a task to be performed by a second device. The method further includes generating instructions for instructing the second device to perform the task, wherein the generated instructions include a verbal command and audibly emitting the verbal command, wherein the audibly emitted verbal command is within audible range of both the user and the second device.