Abstract
Recent advancements in Artificial Intelligence (AI) have created new opportunities to enhance teaching and learning in engineering education. Among these, ChatGPT, an AI language model developed by OpenAI, has gained significant popularity for its ability to generate human-like responses, explain technical concepts, and support problem-solving. While much of the current discourse focuses on student use of ChatGPT, its potential to assist instructors in designing assessments and providing feedback remains underexplored. This gap is particularly relevant in design and manufacturing engineering courses, where instructors often face challenges in crafting open-ended questions, programming-based assessments, and grading complex student submissions with consistency and clarity. To address this gap, this paper investigates the use of ChatGPT as a digital assistant to support assessment-related tasks in design and manufacturing engineering education. Using a reflective case study approach, the work evaluates ChatGPT across five key use cases: (i) Designing Multiple-Choice Questions, (ii) Designing Descriptive Questions, (iii) Designing Computational and Analytical Questions, (iv) Designing Image and Computer Programming-Based Questions, and (v) Designing Rubrics for Grading. Outputs were assessed using a structured pedagogical framework grounded in course learning objectives and Bloom's Taxonomy to evaluate cognitive depth, relevance, and alignment with instructional goals. Findings indicate that ChatGPT can effectively generate relevant and diverse assessment items, reduce instructor workload, and support personalized feedback. However, limitations such as occasional inaccuracies, difficulty generating technical visuals, and the need for instructor oversight highlight the importance of critical evaluation. By outlining both opportunities and constraints, this study offers actionable insights for integrating ChatGPT tools into assessment practices in design and manufacturing engineering education.
Keywords
Get full access to this article
View all access options for this article.
