Abstract: Effective teamwork translates to fewer preventable errors and higher task performance in collaborative tasks. However, in time-critical tasks, successful teamwork becomes highly challenging to attain. In such settings, team members often have only partial observability of their surroundings, face high cost of communication, and struggle to estimate the state and intent of their teammates. To improve teamwork during task execution, we propose an automated task-time team intervention system. Grounded in the notion of shared mental models, the system first detects whether the team is on the same page or not. It then generates effective interventions to improve teamwork. Additionally, by leveraging past demonstrations to learn a model of team behavior, this system minimizes the need for domain experts to specify teamwork models and rules.