ORCID
0009-0007-0870-0342
Keywords
Generative AI, Peer Tutoring, Prompt Engineering, Information Literacy, Source Evaluation, Socratic Dialogue, AI Literacy, Large Language Models, Scaffolded Learning, Metacognitive Development, Higher Education, Iterative Design
Abstract
This chapter explores the design and evaluation of a generative artificial intelligence peer tutor prompt to support college students in identifying and evaluating peer-reviewed sources for academic research. Grounded in literature on peer tutoring, Socratic dialogue, and AI-supported learning, the authors describe an iterative prompt engineering process designed to transform large language models (LLMs) into Socratic-style peer tutors capable of scaffolding student reasoning without completing tasks for them. Five guiding criteria for an effective peer tutor shaped development and evaluation: cognitive congruence, step-by-step guidance, avoiding giving answers, adaptability to student level, metacognitive transparency, and following assignment directions. Across multiple human-centered testing phases involving student workers, classroom implementation, and technical review, the prompt was refined through an evaluation process based on the five guiding criteria. These criteria shaped both an analytical rubric applied to chat transcripts by the authors and student experience surveys. Findings suggest that carefully engineered prompts can improve the pedagogical quality of AI tutoring interactions, particularly when structured with clear organization, explicit process descriptions, and pedagogical rationale. The evaluation also highlights how student AI literacy, assignment clarity, and platform-specific differences shape the effectiveness of AI-mediated peer tutoring interactions. The chapter concludes that while LLMs have inherent capabilities as tutors, they are not "classroom-ready" out of the box. Pedagogical effectiveness requires both careful prompt engineering and intentional AI literacy preparation.
Publication Date
2026
Original Citation
Mair, R., Kelley, M., Wenzel, T., Borowczak, A., Li, Y., & Borowczak, M. (2026). Generative AI peer tutoring to support peer-reviewed source identification and evaluation. In Wiley, D. (Ed.), The pedagogical promptbook : Enacting evidence-based teaching and instructional design practices with generative AI. EdTech Books. https://doi.org/10.59668/2340.26762
Document Type
Book Chapter
Copyright Status
Author retained
Publication Version
Publisher's version
Rights
This work is licensed under a Creative Commons Attribution 4.0 International License.
STARS Citation
Mair, Rae; Kelley, Michelle; Wenzel, Taylar; Borowczak, Andrea C.; Li, Yuqing; and Borowczak, Mike, "Generative AI Peer Tutoring to Support Peer-Reviewed Source Identification and Evaluation" (2026). Faculty Scholarship and Creative Works. 1346.
https://stars.library.ucf.edu/ucfscholar/1346
Included in
Artificial Intelligence and Robotics Commons, Educational Methods Commons, Educational Technology Commons, Information Literacy Commons, Scholarship of Teaching and Learning Commons, Teacher Education and Professional Development Commons