Systems and methods are disclosed herein for continuing playback of a digital tutorial until a user interrupts the playback by signaling to the system that there is an issue or that the user needs help. The system detects a person's utterance (e.g., through passive voice monitoring) and determines that the user's utterance is related to the digital tutorial. The system determines, based on the utterance, which step of the digital tutorial is problematic for the user, and replays the problematic step.