AI-Tutor: A Generative AI Tool for Learning Assistance
Mostafa Mohamed, Computer Science, University of British Columbia – Okanagan, Canada (Canada)
Abdallah Mohamed, Computer Science, University of British Columbia – Okanagan (Canada)
Abstract
Despite the growing popularity of online learning tools, many fail to provide personalized guidance, often leading to a one-size-fits-all approach. This paper presents the development and evaluation of AI-Tutor, an open-source, web-based AI chatbot designed to support students in learning computer science concepts. Using generative AI, the proposed tool provides interactive, real-time tutoring through prompt-engineered responses. The aim is to help students when learning new programming topics and encourages critical thinking during exercises by offering guidance without providing direct answers. The paper discusses two aspects: the design of AI-Tutor and an initial evaluation of its potential to supplement traditional teaching methods. The tool is open-source, which makes it accessible for further academic research and development.
Keywords |
Generative AI in Education, Online Learning Tool |
REFERENCES |
[1] E. Soloway, E. Rubin, B. Woolf, J. Bonar, and W. L. Johnson, Meno-II: An AI-Based Programming Tutor. Ft. Belvoir: Defense Technical Information Center, 1983. [2] “Microsoft copilot: Your everyday AI companion,” available at https://copilot.microsoft.com/ (accessed Aug. 15, 2024). [3] P. Bassner, E. Frankford, and S. Krusche, “Iris: An AI-Driven Virtual Tutor For Computer Science Education,” Arxiv, May 2024. doi:10.1145/3649217.3653543 [4] E. Frankford, C. Sauerwein, P. Bassner, S. Krusche, and R. Breu, “AI-tutoring in software engineering education,” Proceedings of the 46th International Conference on Software Engineering: Software Engineering Education and Training, Apr. 2024. doi:10.1145/3639474.3640061 |