Abstract: A computer-implemented method includes automatically generating, using machine learning, a data structure that stores a knowledge graph for a decision making process that is to be automated. The knowledge graph includes one or more entities, one or more states of each of the entities, and transitions for each of the states. The method further includes creating, from the knowledge graph, a decision tree that represents conditions for one or more parameters that cause the entities to transition from one state to another. The method further includes automatically generating a conversation flow and performing a machine-human conversation with a user to obtain values of the parameters using dialogs from the conversation flow to converse with the user. The method further includes executing the process automatically by traversing the decision tree using the values of the parameters. The method further includes notifying the user of a result of executing the process.