Leveraging Large Language Models in Engineering Design and Product Development: A Snapshot

Large Language Models (LLMs) have emerged as powerful tools capable of understanding and generating human-like text. This presents new opportunities to support engineering design and product development, a discipline that is rich in textual knowledge but traditionally tool-centric. Engineering design is inherently knowledge-intensive and creative, often resulting in a time-consuming process. Recent studies suggest that LLMs can assist in various design activities. This paper surveys the literature up to early 2025 and categorizes current LLM applications within five domains: (1) ideation and conceptual design, (2) requirements engineering and problem definition, (3) knowledge retrieval and documentation, (4) CAD/CAE automation, and (5) systems engineering and decision support. Across these domains, studies indicate that LLMs can enhance creativity, transform unstructured user needs into structured specifications, generate or modify parametric CAD models from natural language prompts, and provide relevant design knowledge through conversational interfaces. Reported benefits include accelerated concept generation, reduced documentation effort, and more intuitive access to legacy information. Key findings, benefits, and limitations are summarized as well as challenges such as issues of accuracy, bias, and integration are addressed. The findings suggest that, with proper integration and oversight, LLMs can significantly enhance engineering design practices, streamlining knowledge-intensive tasks and facilitating innovative design workflows, while highlighting concerns around reliability and ethical considerations. Finally, future research directions are outlined to improve the reliability and effectiveness of LLMs as collaborative tools.