In previous research and development, the developer created Peerceptiv, a website for high school science educators to create customized assignments and assessment rubrics to be completed by hand. In this Phase I project, the research team will develop a new prototype with an artificial intelligence engine to automatically generate new performance-based tasks and assessments for individual and group-based peer learning, and a dashboard that provides educator's insights on student performance.  At the end of Phase I, a pilot study will include eight grade 11 earth science educators with 20 students per class. The researchers will examine whether students can engage with tasks generated by the prototype, if the performance assessments produce valid and reliable results, and if educators believe the results would be useful at providing information to guide instruction.