Clinical reasoning is a core component of medical training, yet learners receive little feedback on their clinical reasoning documentation often due to time constraints of supervisors and lack of a shared mental model. Utilizing a machine learning algorithm for feedback can help overcome these barriers and increase the frequency and quality of feedback in this domain, and ultimately improve documentation quality. In this session, we will present the development of a machine learning algorithm for feedback on clinical reasoning documentation, including an overview of a shared mental model of high-quality clinical reasoning documentation; the development of a predictive model that generates output on quality of clinical reasoning documentation; and an interactive, dynamically updated dashboard embedded in EPIC to provide feedback to residents. We will then facilitate a discussion with the audience about how they could implement this at their home institution.