Background: Tuberculosis (TB) is a communicable disease that mostly affect the lungs, although it can affect other organs in the human body. In the last few years, the trend of antimicrobial resistance is on the higher side due to the overuse and exploitation of existing antitubercular drugs. This has motivated for the search of different approaches like artificial learning (AI) to understand the mechanism of antimicrobial resistance (AMR). Objective: The present study encompasses a concise discussion on the concepts of artificial intelligence (AI), machine learning (ML) and different applications of AI especially in the discovery of anti-tubercular drugs. Methods: The different forms of AI has been explored. Machine learning (ML)is a part of AI that involves large amount of algorithms and data. ML is extensively used in preclinical drug discovery along with other usages such as estimation of target structure, hits identification, ADMET study etc. With the support of AI & ML the genes involved in tb drug resistance, novel targets, various forms of tuberculosis can be identified. Results: AI has provided an enormous opening to hasten the drug discovery process and enhances the chances for the accessibility of novel drugs to patients. The utilization of AI and its subsets provides opportunity to drug discovery at low costs.