The present paper describes the design of a living space comfort regulator using fuzzy logic. Comfort is a fuzzy concept, different for different people and depending on the work done in the space. The paper describes the structure of the system, the available measurements and the available actuators, the measurement fuzzification process and the defuzzification method. Particular attention is paid to the proper selection of the rules in the knowledge base and the design of the inference engine. Finally the system is tested, and shows satisfactory performance. General design guidelines are given, including the case of spaces having different actuators.