Teaching and Educational Methods

Beyond the Textbook: Students’ Experiences Learning Agricultural Policy with an AI Tutor

Robert Huber(a) and Réka Mihálka(b)
(a)ETH Zürich, Agricultural Economics and Policy, (b)ETH Zürich, Department of Management, Technology, and Economics

JEL Codes: A22, Q18
Keywords: Agricultural policy, AI tutor, large language model, retrieval-augmented generation

First Published Online: November 19, 2025

View Full Article (PDF)

Abstract

This study explores the integration of an AI-powered tutor into agricultural policy education at ETH Zürich to enhance the learning experience and provide insights into AI tools in higher education. Based on a large language model (ChatGPT-4.0), the AI tutor was designed to facilitate interactive learning about agricultural policy, specifically tailored to a textbook on Swiss agricultural policy. It provided functionalities such as concept clarification, summaries, knowledge tests, and open-ended discussions for undergraduate students. Over the course of the semester, 15 students used the tutor independently and for exam preparation. Analysis of student interactions revealed that 79 percent of the tutor’s use was for explaining and clarifying concepts, while 9 percent was for summaries and 4 percent for assessments. Students rated their overall satisfaction with the tutor as 3.8 out of 5 and perceived it as a supplementary learning tool. The results provide insights into the benefits, challenges, and ethical considerations of AI in education and highlight the potential for broader applications in other courses. The study contributes to the discourse on AI in higher education and guides the development and integration of AI-enhanced learning tools to improve student engagement and learning outcomes.

About the Authors: Robert Huber (rhuber@ethz.ch) is a researcher and lecturer in the Agricultural Economics and Policy Group at ETH Zurich, Switzerland. Réka Mihalka (mihalkar@ethz.ch) is a lecturer in the Department of Management, Technology and Economics at ETH Zurich.

Acknowledgments: The authors thank the editor and two anonymous reviewers for their helpful and constructive feedback. We also acknowledge Manuel Sudau and Melanie Paschke for their contributions to the survey and manuscript and Sara Amman and Andri Spirig for their assistance with data cleaning and formatting. Finally, we are grateful to the students who participated in the study. Our study had been approved by the ETH Zürich Ethics Commission (EK 2024-N-140). The publication is part of the ETH Zürich-funded Innovedum project: “Assessing the Potential of AI for Scientific Writing Techniques”: https://innovedumprojekte.ethz.ch/3829/en

References

Bentley, S.V., C.K. Naughtin, M.J. McGrath, J. Irons, and P.S. Cooper. 2024. “The Digital Divide in Action: How Experiences of Digital Technology Shape Future Relationships with Artificial Intelligence.” AI Ethics 4:901–915. https://doi.org/10.1007/s43681-024-00452-3

Bick, A., A. Blandin, and D.J. Deming. 2024. “The Rapid Adoption of Generative AI.” NBER Working Paper Series No. 3296. https://doi.org/10.3386/w32966

Chan, C.K.Y., and T. Colloton. 2024. Generative AI in Higher Education: The ChatGPT Effect, 1st ed. Routledge. https://doi.org/10.4324/9781003459026

Deng, R., M. Jiang, X. Yu, Y. Lu, and S. Liu. 2025. “Does ChatGPT Enhance Student Learning? a Systematic Review and Meta-Analysis of Experimental Studies.” Computers & Education 227: 105224. https://doi.org/10.1016/j.compedu. 2024.105224

Finger, R., A. Henningsen, J. Höhler, R. Huber, J. Rommel, and C. Grebitus. 2024. “Open Science in Agricultural Economics.” Q Open 5(3). https://doi.org/10.1093/qopen/qoae029

Gallegos, I.O., R.A. Gallegos, J. Rossi, J. Barrow, M.M. Tanjim, S. Kim, F. Dernoncourt, T. Yu, R. Zhang, and N.K. Ahmed. 2024. “Bias and Fairness in Large Language Models: A Survey.” Computational Linguistics 50(3):1097–1179. https://doi.org/10.1162/coli_a_00524

Huber, R. 2022. Einführung in die Schweizer Agrarpolitik. Zürich: vdf Verlag. https://doi.org/10.3218/4059-3

Kestin, G., K. Miller, A. Klales, T. Milbourne, and G. Ponti. 2025. “AI Tutoring Outperforms in-Class Active Learning: An RCT Introducing a Novel Research-Based Design in an Authentic Educational Setting”. Scientific Reports 15:17458. https://doi.org/10.1038/s41598-025-97652-6

Mollick, E., and L. Mollick. 2024. “Instructors as Innovators: A Future-Focused Approach to New AI Learning Opportunities, with Prompts.” Wharton School Research Paper. https://doi.org/10.2139/ssrn.4802463

Rottner, R., L. Porter, J. Bock, J. Jannone, R.W. Senerchia, J. Ward, and J. Whittinghill . 2025. “AI and the Digital Divide”. In J.R. Corbeil and M. E. Corbeil, eds. Teaching and Learning in the Age of Generative AI. Routledge, pp. 309–331. https://doi.org/10.3218/4059-3

Shear, H.E., L.L. Britton, K.A. Schaefer, B. Thapa, and J.S. Bergtold. 2023. “Artificial Intelligence and the Future of Learning and Assessment in Agricultural and Applied Economics.” Journal of the Agricultural and Applied Economics Association 2(4):838–850. https://doi.org/10.1002/jaa2.98

Silva, B., L. Nunes, R. Estevão, V. Aski, and R. Chandra. 2023. “GPT-4 as an Agronomist Assistant? Answering Agriculture Exams Using Large Language Models.” arXiv preprint 2310.06225. https://doi.org/10.48550/arXiv.2310.06225

Stolpe, K., and J. Hallström. 2024. “Artificial Intelligence Literacy for Technology Education.” Computers and Education Open 6:100159. https://doi.org/10.1016/j.caeo.2024.100159

van Deursen, A., and J. van Dijk. 2011. “Internet Skills and the Digital Divide.” New Media & Society 13(6):893–911. https://doi.org/10.1177/1461444810386774

Xiao, P., Y. Chen, and W. Bao. 2023. “Waiting, Banning, and Embracing: An Empirical Analysis of Adapting Policies for Generative AI in Higher Education.” SSRN. https://doi.org/10.2139/ssrn.4458269

Yu, H., and Y. Guo. 2023. “Generative Artificial Intelligence Empowers Educational Reform: Current Status, Issues, and Prospects.” Frontiers in Education 8. https://doi.org/10.3389/feduc.2023.1183162