Examples are disclosed that relate to methods, computing devices, and systems for determining a user's readiness for an operational task. One example provides a method comprising, during a training phase, receiving training input data including, for each user training session, a training data pair including, as input, a distance of travel, a mode of travel, and one or more environmental conditions, and as ground truth output, a time elapsed for performance of the training task. An artificial intelligence (AI) performance model is trained to model user performance of the training task based on the training data pairs. During a run-time phase, operational input data is received that is associated with an operational task performed by the user. The performance model is used to infer a predicted time elapsed for performance of the operational task.