Hostname: page-component-7b7567c8c-wxvwp Total loading time: 0 Render date: 2026-11-17T21:21:21.521Z Has data issue: false hasContentIssue false

Structured prompting for design for multi-X: evaluating LLM support in early prosthetic device design

Published online by Cambridge University Press:  02 July 2026

Adrian Mercieca*
Affiliation:
University of Malta, Malta
Philip Farrugia
Affiliation:
University of Malta, Malta
Jonathan Borg
Affiliation:
University of Malta, Malta

Abstract:

This paper investigates how prompt structure influences the use of Large Language Models in early engineering design. A structured prompting framework aligned with the engineering design cycle is proposed to support Design for Multi X reasoning and more coherent problem exploration. Using a prosthetic knee-cover case study, six engineering designers engaged with both generic and structured prompting workflows. A mixed methods study examines how prompt organisation shapes LLM assisted reasoning, problem framing and the articulation of design constraints and considerations.

Information

Type
ARTIFICIAL INTELLIGENCE AND DATA-DRIVEN DESIGN
Creative Commons
Creative Common License - CCCreative Common License - BYCreative Common License - NCCreative Common License - ND
This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (https://creativecommons.org/licenses/by-nc-nd/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is unaltered and is properly cited. The written permission of Cambridge University Press must be obtained for commercial re-use or in order to create a derivative work.
Copyright
The Author(s), 2026
Figure 0

Figure 1.Figure 1 long description.a) Human-AI prompt interaction for the Multi-X Structured template b) example of prompt structure

Figure 1

Table 1.Three prompt structure per phase, with multi-X and trade-off focus

Figure 2

Table 2.Coding codebook excerpt and operational definitions

Figure 3

Table 3.Descriptive summary of core metrics by prompting condition (generic vs structured prompting)

Figure 4

Figure 2.Multi-X mentions per 100 words for each design activity

Figure 5

Figure 3.Mean trade-off depth

Figure 6

Table 4.Mean Likert ratings from engineering designers