A system and a method for requirement gathering in process automation is disclosed. The method includes capturing one or more application screens along with one or more actions performed by a user on the one or more corresponding application screens; extracting one or more features from one or more captured application screens; determining a level of similarity between one or more extracted features of the corresponding one or more application screens and one or more prestored features of corresponding one or more prestored application screens; creating clusters of the one or more actions performed by the user based on a determined level of similarity; creating one or more nodes of the at least one application screens based on clustering of the one or more actions; generating a specification template for process automation based on the one or more nodes of the at least one application screens.