CONFERENCES
E&PDE 2026 - 28th International Conference on Engineering & Product Design Education
The Conference will bring together representatives from education and industry interested in sharing new perspectives on design education.
Knowledge Base Repository
In addition to research papers, the Design Society is developing several valuable resources for those interested in the study of design. These include a repository of PhD theses, a library of case studies and transcripts of design activities, and an archive of our newsletters. Please note that these resources are accessible exclusively to Design Society members.
AI-GENERATED FORMATIVE FEEDBACK FOR ENGINEERING LAB REPORTS
Pyle, Richard; Ross, Joel; Nassehi, Aydin
Type:
Year:
2026
Editor:
Buck, Lyndon; Brisco. Ross; Bohemia, Erik
Author:
Series:
E&PDE
Institution:
University of Bristol, United Kingdom
Page(s):
373 - 378
DOI number:
ISBN:
978-1-912254-24-8
ISSN:
3005-4753
Abstract:
This project examined the use of AI-generated formative feedback in a first-year engineering unit, focusing on developing students’ AI literacy and critical thinking. Students who opted in received feedback on draft laboratory reports from a locally deployed large language model, chosen to ensure data privacy and, potentially, to reduce the environmental footprint associated with external services. The feedback was discussed in small groups during an in-person workshop. It is hoped that, alongside peer review, this offers complementary opportunities for a diverse cohort to engage critically with feedback Of 830 enrolled students, 390 submitted a draft and 374 opted in for AI feedback. Pass rates on the subsequent summative report were 70% for those receiving AI feedback versus 57% for those who did not. This difference remains confounded by known correlations between engagement with formative activities and overall attainment. A deliberate design feature was the inclusion of intentional inaccuracies in each student’s feedback. This was explained to students beforehand and intended to promote scrutiny of feedback rather than passive acceptance of AI output. The activity was supported by a short presentation on responsible AI use and ethical considerations, informing discussions about trust, reliability, and the role of AI in education. Survey responses were limited (n = 25), but 71% of respondents found the feedback useful and 89% revised their work as a result. Students valued clarity, speed, and rubric-based structure but expressed mixed views on the introduced inaccuracies—some constructive, others distracting.
Keywords:
