Centering Educators in AI-Assisted Instructional Loops with a Customizable Platform for STEM Virtual Teaching Assistants

This project aims to serve the national interest by developing an empirically validated software tool that will provide scalable, personalized support to students in large classrooms. The goal of this IUSE:EDU Level 2 Engaged Student Learning project is to develop an AI-driven software system that integrates educators' materials and rules that guide large language models to provide students with Virtual Teaching Assistants (VTAs) that produce tailored responses that directly reference specific course content. The VTAs will be designed to match the instructor's teaching style and goals, offer responsive support for students, and will provide a model for responsible AI integration in education. The overarching goal of the project is to provide students with personalized educational support while equipping educators with the tools they need to scale their teaching capabilities and deepen their insights into student learning. This project seeks to develop an AI-driven platform creating VTAs that integrates educators' materials and rules, which will guide large language models in producing tailored responses that directly reference specific course content. The system will consist of several key components: a subsystem for sorting and processing student inquiries, a subsystem to include prompt constraints and keep course adherence, a safeguard module to ensure the ethical use of AI in education, and an analytical module for detailed evaluation of student interactions. The system's retrieval-augmented generation framework will aim to match student queries with relevant content, ensuring accuracy and context. With features for privacy, secure data management, and real-time analytics, the system is intended to enable educators to scale support effectively and provide personalized learning experiences aligned with course goals. The NSF IUSE:EDU Program supports research and development projects to improve the effectiveness of STEM education for all students. Through the Engaged Student Learning track, the program supports the creation, exploration, and implementation of promising practices and tools. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.