Skip to content

Pedagogy-guided integration of generative AI in undergraduate engineering education

Sep 2026 · Journal of Applied Research in Higher Education · 0 citations · 20 references

TL;DR

The findings suggest that the educational value of generative AI depends on pedagogical orchestration, guided prompting and reflection rather than simple access to the tool.

Abstract

This study examines whether a pedagogy-guided, artificial intelligence (AI)-assisted learning environment can improve learning performance and student perceptions in undergraduate engineering education. Rather than positioning generative AI as an answer-generating tool, the study frames it as a scaffold embedded within a structured teaching process. A quasi-experimental design was implemented in an undergraduate engineering course in Taiwan. Eighty-two students participated across an AI-assisted group and a comparison group receiving conventional instruction. The intervention followed four recurring stages: problem introduction, AI-supported exploration, critical reflection and discussion with feedback. Quantitative evidence was drawn from five rubric-assessed problem-solving assignments and a post-course questionnaire administered to the AI-assisted cohort, while qualitative evidence came from students' reflective writing. Because the questionnaire was administered only to the AI-assisted cohort, its results are reported descriptively rather than as between-group effects. The AI-assisted cohort showed higher composite assignment performance and reported strong engagement, perceived usefulness and problem-solving confidence. Qualitative findings showed that structured reflection helped students question AI-generated responses, identify limitations and refine their own reasoning rather than accept outputs uncritically. As the comparison group came from a previous semester, assignments were scored by the course instructor and prior AI exposure was not measured systematically, the findings should be interpreted as promising exploratory evidence rather than definitive causal proof. The findings suggest that the educational value of generative AI depends on pedagogical orchestration, guided prompting and reflection rather than simple access to the tool. The paper offers a classroom-tested model for integrating generative AI into higher engineering education in a pedagogically meaningful and ethically responsible way.

View source

Similar papers

#artificial intelligence Conference Open access Apr 2020

ECCOLA - a Method for Implementing Ethically Aligned AI Systems

The method, ECCOLA, is presented, which aims at making the high-level AI ethics principles more practical, making it possible for developers to more easily implement them in practice.

Ville Vakkuri, Kai-Kristian Kemell, P. Abrahamsson · 64 citations · ⚡6
#computer vision Review Apr 2024

AI-powered Code Review with LLMs: Early Results

The goal is to not only refine the accuracy of the LLM-based tool but also to underscore its potential in streamlining the software development lifecycle through proactive code improvement and education.

Z. Rasheed, Malik Abdul Sami, Muhammad Waseem et al. · 62 citations · ⚡3
#computer vision Open access Mar 2024

LLM-based agents for automating the enhancement of user story quality: An early report

The use of large language models to automatically improve the user story quality in Austrian Post Group IT agile teams is explored, with a reference model for an Autonomous LLM-based Agent System developed and implemented at the company.

Zheying Zhang, M. Rayhan, Tomas Herda et al. · 48 citations · ⚡4
#computer vision Review Mar 2024

System for systematic literature review using multiple AI agents: Concept and an empirical evaluation

This paper introduces a novel multi-AI-agent system designed to fully automate SLRs, and demonstrates how it substantially reduces the time and effort traditionally required for SLRs while maintaining comprehensiveness and precision.

Abdul Malik Sami, Z. Rasheed, Kai-Kristian Kemell et al. · 44 citations · ⚡2
#computer vision Feb 2024

Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis

The proposed LLM-based multi-agent system automates qualitative data analysis process, creating opportunities for researchers and practitioners, and future improvements focus on enhancing multilingual performance and integrating continuous expert feedback.

Z. Rasheed, Muhammad Waseem, Aakash Ahmad et al. · 41 citations

Related blog posts

GPT-Lab Sep 17, 2026

Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering

AI is making software generation faster, but speed does not remove the need for expertise. As more work is delegated to AI, tacit knowledge may become one of the most important human advantages in software engineering. The post Beyond Prompt Engineering: The Role of Tacit Knowledge in Software Engineering appeared first on GPT-Lab.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.