Exploiting knowledge to guide the evolutionary process in evolutionary computing is a concept that has the potential to increase the performance of evolutionary algorithms. The research question of this paper is “Can heuristics derived from past experiences be incorporated into evolutionary computing in order to increase the performance?” In order to answer the research question the following hypothesis is developed: “A heuristically-guided mutation of decision trees will outperform randomly mutated decision trees in terms of classification accuracy.”The methodology for answering the hypothesis is an experiment that tests a knowledge-guided mutation of a decision tree using heuristics created from prior decision trees as a form of knowledge. This is compared with a random mutation of the same decision tree. This experiment supports the theory that using knowledge in the form of heuristics to guide mutation will produce a difference in the performance of the classification of data instances. This supports the need for further research into knowledge guided evolutionary algorithms.