Teacher Moments is an open source platform that allows the authoring of simulations used for education which we recently revised to integrate intelligent coaching agents. The initial simulation development for Teacher Moments focused on teacher education, but the platform is actively used for professional development with nurses, psychologists, police officers, judges, and attorneys. Simulations can range in complexity from single-user simulations to multi-user role-play simulations. Single-user simulations provide opportunities for participants to respond using text or audio inputs while multiuser simulations extend those response types to include chat functionality. To support participant learning, Teacher Moments simulations can now be configured to include intelligent coaching agents that review participant inputs, identify salient patterns in text or speech, and respond with feedback and coaching supports. Teacher Moments can be configured to incorporate text or audio binary classifiers or include conversational agents into the chat feature. Once a classifier is configured there is functionality to dynamically display content based on audio or text classification when authoring the simulation. In addition, conversational agents can interject comments into the chat directed at either a particular participant or to all participants in a chat. Finally, there is a new integrated labeling component that supports collecting binary labels from participants for text or audio data, which can be used either to validate the accuracy of a classifier or to establish training data for a classifier. In this demo, we will: 1) highlight GitHub repositories designed to support the deployment of classifiers that can be integrated into Teacher Moments; 2) demonstrate a conversational agent integrated into the chat feature to provide intelligent supports; 3) illustrate how binary classification can trigger the dynamic display of content providing options for dynamic learning supports; and 4) demonstrate how the labeling component can be used for either validation of a classifier or collection of training data.