This project studied the utility of a machine learning-based assessment system for supporting middle school science teachers in making instructional decisions based on automatically generated student reports (AutoRs). The assessments target three-dimensional (3D) science learning by requiring students to integrate scientific practices, crosscutting concepts, and disciplinary core ideas to make sense of phenomena or solve complex problems. The project aims to (a) develop automatically generated student reports (AutoRs) for three-dimensional (3D) science assessments to assist middle-school teachers in noticing, attending to, and interpreting information in ongoing classroom teaching, and (b) develop effective pedagogical content knowledge supports (PCKSs) to improve teachers’ use of AutoRs to make effective decisions for instructional moves. Achieving these goals will significantly improve classroom assessment practices, increase teachers’ instructional decision-making, and provide students with customized science learning.