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.
How Ready is Agentic AI for Engineering Design? A Survey-Grounded Task Taxonomy and Readiness Assessment
Berger, Elias; Dhillon, Singh, Abhijeet; Nambiar, Mithil; Mehlstäubl, Jan; Saske, Bernhard; Paetzold-Byhain, Kristin
Type:
Year:
2026
Editor:
Paetzold-Byhain, K.; Krause, D.; Wartzack, S. and Koch, A.
Author:
Berger, Elias; Dhillon, Singh, Abhijeet; Nambiar, Mithil; Mehlstäubl, Jan; Saske, Bernhard; Paetzold-Byhain, Kristin
Series:
DfX
Institution:
Dresden University of Technology, Germany; MAN Truck & Bus SE, Germany; MAN Truck & Bus India Pvt. Ltd, India
Page(s):
060-069
DOI number:
Abstract:
Generative and Agentic AI hold promise for mechanical engineering design, yet it remains unclear which tasks are automatable and how ready current systems actually are. We survey 20 engineers at a commercial vehicle manufacturer and derive a taxonomy of 24 routine engineering design tasks. We then assess current agentic LLM systems against this taxonomy using Machine Learning Technology Readiness Levels. No task exceeds level 4 of 9 and most remain at 2–3: capabilities can be demonstrated but have not crossed from research prototype to product. The tasks dominating current AI-for-CAD research are also those engineers prioritise least, indicating a misalignment between research focus and engineering practice.
Keywords:
