This research proposes a design method that combines a probability based decision strategy and design grammars (production rules) into a “design agent” for system development. This decision strategy can be evolved by applying a genetic algorithm (GA) to facilitate the exploration of a multi-domain design space in a topologically open-ended manner, and still efficiently find appropriate design configurations. Probability based decision making is applied at each stage of topology development. A design of a low pass filter is used as a case study. Experimental results show that a design agent demonstrates steady performance in terms of the overall fitness of its designs. A superior design agent can easily produce designs of good quality and reach the best design.