In is paper, a new technique in complex adaptation is investigated. By presenting the closest retrieved cases to a neural network, it learns about the domain of the problem being solved. The new problem is then fed to the trained neural network and the output becomes the solution to that problem. The methodology is applied to a problem in the steel construction and the sought output is the cost estimation of pre-engineered steel buildings.Several experiments are conducted to prove that these steps are successful. System verification is done and shows that both the system and the methodology are successful to develop a complete adaptation mechanism in CBR.