Hello all, Before I get into the details of what I am trying to do and the advice that I am asking for, I just want to make sure that this is the right place to ask for help in developing the basic flow and outline. In short, I am going to develop subject specific AI pedagogical agents for an Intelligent Tutoring System. So far, it seems like the best tools to do this are using TensorFlow Python API/Keras and perhaps in Colab or Jupyter notebooks. My goal is to ML train the bots so that they are highly personalized and adapt to the student in Realtime during a 1-hour tutoring session. Using an ITS psychometric modeling framework, I could extract knowledge components and skills and use that to perform knowledge assessment for the student model. This ITS model would entail a student profile matrix (A), Observed response matrix (R), and Q matrix for building the student model (Q). Part of it would also entail building the student model (mapping of skills to items (questions) so that Bayesian Tracing Knowledge can be employed that is Realtime Adaptive learning. This would also entail using a Deep Learning Knowledge Tracing (DKT) Recurrent Neural Networks and train the Q-Learning Algorithm. So, it seems like the first place to start is with the Student Model and develop the items or questions. But, what questions will I need to ask so that the best student profile is generated? Any help is greatly appreciated, John