The introduction of large language models in the form of ChatGPT at the end of 2022, marked the beginningof the widespread democratization of artificial intelligence. This is spawning a entirely new area of researchinto application of this technology. This paper presents a novel approach to generate configuration rules, anddesign concepts using ChatGPT. The objective is to demonstrate how large language models models can aidin automating the engineering design process. In this paper the configuration of aircraft hybrid propulsionsystems is studied as an example. It is shown how a system configuration can be generated and presentedin the form of UML component diagrams. Large Language Models usually have an element of randomnessinserted in their response. This makes them inherently non-deterministic, and the result is not always correct.Therefore, statistical properties are studied such that the probability of getting a correct result can be estimated,and prompts can be tweaked to provide the best result. This is particularly useful when a prompt is separatedinto a general part that can be reused for similar tasks, and one specific part.It is also shown how these models can used in consecutive step to formulate a simulation model and executeit within the framework of ChatGPT-4, or be exported to more dedicated simulation models for more advancedsimulations. Also optimization can be included. The study shows promising results, and it shows that thereis an immense potential for AI in engineering system design, and we are just in the beginning of applying thistools.