In this paper, we describe a new air-conditioning system that takes human behavior into account. We introduce a method of predicting the indoor comfort level distribution by combining computational fluid dynamics (CFD) and Internet of Things (IoT), and a concept of air-conditioning guidance that encourages human behavior by using this method. In particular, we discuss the method of optimizing parameter for the CFD analysis used in the system, which ensures acceptable computational speed and accuracy in the proposed guidance system, by comparing the results of experiments using a small room model.