The agriculture and economy of India are driven by Livestock sector. Despite rapid expansion of livestock sector, animal diseases are hindering its growth and development. Artificial intelligence (AI) has emerged as a rescue to treat animal diseases by providing advanced diagnostic technologies which results in less economic loss of farmers. Expert Systems (ES) are a branch of artificial intelligence that has been developed to efficiently diagnose diseases. These systems come across uncertainties during the course of Practical reasoning. Several techniques have been developed to deal with the uncertainties. Certainty Factor (CF) is one of those techniques. To efficiently diagnose the diseases, Rule-based Expert Systems are used which utilize the rules provided by the experts. These experts assign a Confidence Factor to the rules which represent the diagnostic accuracy of these rules. The ability of the system to diagnose remains stagnant as the value of Confidence Factor remains as it was provided by the Expert. However, if the Confidence Factor of these rules changes with the results of diagnose, it will strengthen the inference power of these systems. By promoting or demoting the Confidence Factor in rules, this research aims to strengthen the capability of inference engine and thereby enhancing the overall performance of Expert System.