AI-Mediated Feedback in Computer-Aided Drafting Education: Exploratory Evidence on Student Performance and Perceptions

Víctor A. Erazo-Arteaga; Santiago Marcelo Vacas Palacios; Marcelo Bayardo Cisneros Rúales

doi:10.3991/ijep.v16i6.61849

Authors

Víctor A. Erazo-Arteaga Universidad Técnica del Norte, Ibarra, Ecuador https://orcid.org/0000-0001-5915-1864
Santiago Marcelo Vacas Palacios Universidad Técnica del Norte, Ibarra, Ecuador https://orcid.org/0000-0003-3304-3843
Marcelo Bayardo Cisneros Rúales Universidad Técnica del Norte, Ibarra, Ecuador https://orcid.org/0000-0002-8818-6502

DOI:

https://doi.org/10.3991/ijep.v16i6.61849

Keywords:

Educational feedback, Artificial Intelligence (AI), academic performance, practical learning , quasi-experimental design , higher education , computer-assisted learning , AI-mediated feedback , student perceptions

Abstract

Large higher-education classes make timely feedback during practical sessions difficult, encouraging the use of artificial intelligence (AI) as a complementary resource in technical education. This study examined AI-mediated feedback during computer-aided drafting (CAD) activities using structured prompts and task segmentation, alongside instructor-provided feedback across alternating phases. Academic performance and student perceptions were analyzed in a classroom environment. A quasi-experimental within-subjects ABAB design was implemented with 34 first-year Industrial Engineering students over 20 weeks, as the curriculum progressed from two-dimensional (2D) drafting to three-dimensional (3D) modeling. Results showed significant performance variation, with lower scores in later phases involving greater procedural demands. Since feedback modalities were embedded within the curricular progression, these differences cannot be interpreted as isolated causal effects of feedback modality. Students rated both modalities positively and considered AI-mediated feedback useful for resolving specific doubts, although not more useful than instructor feedback, particularly in 3D tasks. AI-mediated feedback may complement CAD instruction, depending on task complexity, prompt precision, response reliability, and instructor guidance.

Author Biographies

Víctor A. Erazo-Arteaga, Universidad Técnica del Norte, Ibarra, Ecuador

Víctor A. Erazo-Arteaga is a Mechanical Engineer with a Master’s degree in Design and Industrial Automation. His academic background also includes university studies in Technical Pedagogy, followed by a Master’s degree in Educational Research Methods. He is a professor and researcher at Universidad Técnica del Norte, Ecuador. His research interests include engineering education, artificial intelligence in education, computer-aided design (CAD), manufacturing technologies, and educational innovation. (EMAIL: vaerazo@utn.edu.ec).

Santiago Marcelo Vacas Palacios , Universidad Técnica del Norte, Ibarra, Ecuador

Santiago Marcelo Vacas Palacios is an Agroindustrial Engineer with a Master’s degree in Administration, Quality Management, and Productivity. He is a faculty member and researcher in the Industrial Engineering Program at Universidad Técnica del Norte, Ecuador. His research interests include research methods, pedagogy, engineering education, university-level teaching, and optimization techniques. (EMAIL: smvacas@utn.edu.ec).

Marcelo Bayardo Cisneros Rúales, Universidad Técnica del Norte, Ibarra, Ecuador

Marcelo Bayardo Cisneros Rúales is a Commercial Engineer and Business Administrator with a Master’s degree in Business Administration. He is a faculty member and researcher in the Industrial Engineering Program at Universidad Técnica del Norte, Ecuador. His research interests include educational research, industrial engineering, and management education. (EMAIL: mbcisneros@utn.edu.ec).

References

[1] N. K. Mandal, “Importance of student feedback in improving mechanical engineering courses,” International Journal of Mechanical Engineering Education, vol. 47, no. 3, pp. 227–245, Jul. 2019, doi: 10.1177/0306419018759800.

[2] M. Thurlings and M. van Diggelen, “Perceptions of practical knowledge of learning and feedback among academic teachers,” European Journal of Engineering Education, vol. 46, no. 1, pp. 139–160, Oct. 2019, doi: 10.1080/03043797.2019.1677559.

[3] D. Alique and M. Linares, “The importance of rapid and meaningful feedback on computer-aided graphic expression learning,” Education for Chemical Engineers, vol. 27, pp. 54–60, Apr. 2019, doi: 10.1016/j.ece.2019.03.001.

[4] L. Hua, L. Guo, N. Zheng, Y. Lu, J. Xu, and J. Deng, “Proactive framework for evaluating retrieval-augmented generation-based learning assistants in engineering education,” Computer-Aided Civil and Infrastructure Engineering, vol. 40, no. 26, pp. 4651–4668, Nov. 2025, doi: 10.1111/mice.70063.

[5] A. Lathigara, P. Tanna, N. Bhatt, H. Durani, and K. Thumar, “Reimagining Fairness by Inclusive Assessment Practices for Diverse Engineering Cohorts,” Journal of Engineering Education Transformations, vol. 39, no. S2, pp. 195–201, Jan. 2026, doi: 10.16920/jeet/2026/v39is2/26024.

[6] Z. Ngcobo, “Keeping Pace with 21st Century Skills: The Role of Computer-Aided Design in Teaching Engineering Graphics and Design,” International Journal of Learning, Teaching and Educational Research, vol. 24, no. 12, pp. 546–568, Dec. 2025, doi: 10.26803/ijlter.24.12.24.

[7] B. N. Guler, S. Sajadi, A. Alenezi, and D. Bairaktarova, “From Doubt to Drive: How Instructional Modality and Self-Efficacy Shape Motivation in Remedial Spatial Visualization Courses,” International Journal of Engineering Pedagogy, vol. 14, no. 5, pp. 37–50, Jun. 2024, doi: 10.3991/ijep.v14i5.46097.

[8] A. Rahman et al., “Artificial intelligence innovations challenges and emerging trends in engineering education,” Discover Education, vol. 5, no. 1, Feb. 2026, doi: 10.1007/s44217-026-01137-1.

[9] T. Alasmari, “Artificial Intelligence and M-Learning in Arabic Countries: Innovations, Trends, and Regional Perspectives,” International Journal of Interactive Mobile Technologies, vol. 19, no. 5, pp. 170–194, Mar. 2025, doi: 10.3991/ijim.v19i05.52735.

[10] L. T. Ameen, M. R. Yousif, N. A. Jasim Alnoori, and B. H. Majeed, “The Impact of Artificial Intelligence on Computational Thinking in Education at University,” International Journal of Engineering Pedagogy, vol. 14, no. 5, pp. 192–203, Jun. 2024, doi: 10.3991/ijep.v14i5.49995.

[11] L. Li and M. Bertrand, “Fostering critical thinkers and future designers: Design fiction pedagogy in AI education,” Think. Skills Creat., vol. 59, Mar. 2026, doi: 10.1016/j.tsc.2025.101962.

[12] L. Holubnycha et al., “AI-Powered Teaching: Literature Review of ChatGPT’s Impact on University Educators,” International Journal of Interactive Mobile Technologies, vol. 19, no. 15, pp. 41–65, Aug. 2025, doi: 10.3991/ijim.v19i15.54275.

[13] D. A. Varsos, N. C. Zygouris, K. M. Kolomvatsos, A. N. Dadaliaris, and G. Dimitriou, “Prediction of Secondary-School Student Cognitive Performance in Informatics,” International Journal of Engineering Pedagogy, vol. 16, no. 1, pp. 66–86, Mar. 2026, doi: 10.3991/ijep.v16i1.56637.

[14] Y. Dai, “Why students use or not use generative AI: Student conceptions, concerns, and implications for engineering education,” Digital Engineering, vol. 4, Mar. 2025, doi: 10.1016/j.dte.2024.100019.

[15] M. Alghazo, V. Ahmed, and Z. Bahroun, “Exploring the applications of artificial intelligence in mechanical engineering education,” 2024, Frontiers Media SA. doi: 10.3389/feduc.2024.1492308.

[16] T. Köring, D. Gerhard, and M. Neges, “Design and Implementation of a Skill Development Program in AI Driven Generative Engineering,” in DS 131: Proceedings of the International Conference on Engineering and Product Design Education (E&PDE 2024), Institute for Product and Service Engineering, Digital Engineering Chair, Ruhr-University Bochum, Germany, 2024, pp. 223–228. doi: 10.35199/EPDE.2024.38.

[17] L. W. Jianwu et al., “Artificial intelligence-enabled evaluating for computer-aided drawings (AMCAD),” International Journal of Mechanical Engineering Education, vol. 52, no. 1, pp. 3–31, Jan. 2024, doi: 10.1177/03064190231175231.

[18] O. Kravchenko and S. Green, “Future proofing computer-aided design education through ai-driven e-learning,” in DS 131: Proceedings of the International Conference on Engineering and Product Design Education (E&PDE 2024), H. Grierson, E. Bohemia, and L. Buck, Eds., United Kingdom: Imperial College London, 2024, pp. 336–341. doi: 10.35199/EPDE.2024.57.

[19] V. A. Erazo-Arteaga, “Personalization of tasks as a learning methodology to avoid dishonesty in higher education,” Formacion Universitaria, vol. 16, no. 6, pp. 47–60, 2023, doi: 10.4067/S0718-50062023000600047.

[20] C. Cebolla, J. Santoro, and J. García, AutoCAD 2017. Curso práctico. Madrid, España: RA-MA Editorial, 2017.

[21] L. Graefe, S. Hahn, and A. Mayer, “On the Relationship between ANOVA Main Effects and Average Treatment Effects,” Multivariate Behav. Res., vol. 58, no. 3, pp. 467–483, 2023, doi: 10.1080/00273171.2022.2068122.

[22] D. Afshartous and R. A. Preston, “Key results of interaction models with centering,” Journal of Statistics Education, vol. 19, no. 3, 2011, doi: 10.1080/10691898.2011.11889620.

[23] S. W. Jarantow, E. D. Pisors, and M. L. Chiu, “Introduction to the Use of Linear and Nonlinear Regression Analysis in Quantitative Biological Assays,” Curr. Protoc., vol. 3, no. 6, Jun. 2023, doi: 10.1002/cpz1.801.

[24] G. Zacharis and S. Papadakis, “Can AI grade like a human? Validity, reliability, and fairness in university coursework assessment,” Educational Process: International Journal, vol. 19, pp. 1–22, 2025, doi: 10.22521/edupij.2025.19.591.

[25] C. R. Patel, S. Patel, C. B. Rathod, A. Vagadia, R. R. Modi, and A. Kumar, “AI-Powered Gamification in Computer Engineering Education: A Mixed-Methods Study on Engagement, Learning Outcomes, and Personalization,” Journal of Engineering Education Transformations, vol. 39, no. Special Issue 3, pp. 42–48, Feb. 2026, doi: 10.16920/jeet/2026/v39is3/26096.

[26] S. Altikriti and Z. Nemrawi, “The Use of ChatGPT as a Learning Tool Among Jordanian Students in Technical Universities: Attitudes and Perceptions,” International Journal of Interactive Mobile Technologies, vol. 19, no. 5, pp. 144–158, Mar. 2025, doi: 10.3991/ijim.v19i05.52049.