Currently, the applications of Large Language Models (LLMs) have expanded to diverse areas, from code generation to the medical diagnosis of various pathologies. This work aims to explore what an LLM can achieve using information from CFD simulations of turbulent flow in a manifold, and to determine whether users or students can employ it as a guide for conducting this type of analysis. Through a case study, it is intended to investigate the following aspects of an LLM: (1) the type of information it handles regarding the behavior of turbulent flow within a manifold, (2) whether it identifies the boundary conditions necessary to perform a CFD simulation in a manifold, (3) its capacity to provide recommendations for improving CFD simulations based on the results obtained, (4) whether it can predict the results of CFD simulations based on previous results, and (5) whether users or students can use it as a guiding tool for performing CFD simulations. Among the findings, it was discovered that the LLM used has sufficient information on turbulent flows within a manifold and can make recommendations to improve the results of CFD simulations. It was also identified that LLM offers a user-friendly environment and that it is possible to predict CFD simulation results by varying the manifold boundary conditions. On the other hand, the LLM¿s prediction model trained on CFD simulation data yielded RMSEs of 0.029 m/s for flow velocity and 0.33 °C for temperature, and R2 values of 0.999 for flow velocity and 0.998 for temperature.
