The AI Tutor in Engineering Education: Design, Results, and Redesign of an Experience in Hydrology at an Argentine University

TL;DR

This study examines the design, failure, and successful redesign of an AI Tutor intervention in a Latin American engineering course, highlighting the importance of strict process controls and assessment protocols to ensure genuine learning and academic integrity.

Contribution

It introduces a comprehensive, empirically tested protocol for AI-assisted STEM education emphasizing process controls and verifiable student interactions.

Findings

Initial AI intervention failed with 0% pass rate and high similarity issues.

Redesign with strict evidence controls improved scores and ensured genuine engagement.

Proposes a transferable assessment protocol based on 'auditable personal zones'.

Abstract

The emergence of Generative Artificial Intelligence (GenAI) has reshaped higher education, presenting both opportunities and ethical-pedagogical challenges. This article presents an empirical case study on the complete cycle (design, initial failure, redesign, and re-evaluation) of an intervention using an AI Tutor (ChatGPT) in the "Hydrology and Hydraulic Works" course (Civil Engineering, UTN-FRT, Argentina). The study documents two interventions in the same cohort (n=23). The first resulted in widespread failure (0% pass rate) due to superficial use and serious academic integrity issues (65% similarity, copies > 80%). This failure forced a comprehensive methodological redesign. The second intervention, based on a redesigned prompt (Prompt V2) with strict evidence controls (mandatory Appendix A with exported chat, minimum time $\geq$ 120 minutes, verifiable numerical exercise) and a refined rubric (Rubric V2), showed significantly better results: a median score of 88/100 and verifiable compliance with genuine interaction processes. Using a mixed-methods approach (reproducible document analysis and rubric analysis), the impact of the redesign on integrity and technical performance is evaluated. The results demonstrate that, without explicit process controls, students prioritize efficiency over deep learning, submitting documents without real traceability. A transferable assessment protocol for STEM courses is proposed, centered on "auditable personal zones," to foster higher-order thinking. The study provides key empirical evidence from the context of a public Latin American university.