Clemson University computer science students teamed up with global AI leader NVIDIA to develop an AI-powered virtual teaching assistant designed to enhance learning and uphold academic integrity.
They built the tool using NVIDIA’s cutting-edge AI Blueprint for Retrieval-Augmented Generation (RAG), creating a system that helps students strengthen their understanding of core concepts while offering scalable, around-the-clock support. The assistant addresses growing demand for tutoring in high-enrollment STEM courses and demonstrates how AI can responsibly support education.
“This project shows what’s possible when students work directly with advanced AI technology from industry leaders like NVIDIA,” said Carrie Russell, professor of practice in Clemson’s School of Computing. “Our team tackled a pressing challenge in education and delivered a solution that’s both innovative and practical. We’re proud to collaborate with NVIDIA on work that has the potential to transform learning at scale.”
Karthick Iyer, Vice President, Engineering at NVIDIA, said he was impressed with the students’ ability to turn cutting-edge AI tools into a practical solution for real educational challenges.
“It’s inspiring to see Clemson students apply NVIDIA’s AI Blueprint for RAG to create a tool that directly tackles real-world issues in education,” Iyer said. “This collaboration shows the power of pairing AI innovation with hands-on student learning, and we’re thrilled to support projects that advance both technology and education.”
Students Camden Spehl, Kyle Zheng, Jaylen Goddard, and Cordarro Higgins Redman collaborated with Vinay Raman, a senior deep learning scientist at NVIDIA, to bring the project to life.
Read their blog post here.
The virtual teaching assistant is designed to guide students through problem-solving steps, rather than simply providing answers. It uses retrieval-augmented generation to pull in the most relevant course materials—like lecture notes, readings, and rubrics—and then crafts responses that explain key concepts, show examples, and prompt students with follow-up questions.
The system also integrates NVIDIA NeMo Guardrails, which help ensure academic integrity by intercepting “just give me the answer” requests and redirecting them into constructive, learning-focused interactions. The assistant connects directly with the university’s learning platform, allowing it to personalize guidance based on the student’s current coursework and deadlines.
The project was supported in part by NVIDIA’s Academic Grant Program, which provided compute resources to help bring the assistant to life. Read more here. Looking ahead, Clemson will pilot the virtual teaching assistant in select School of Computing courses starting this fall. The pilot will allow the team to refine the tool based on direct student engagement and continue showcasing the real-world potential of NVIDIA’s AI technologies.
