When coming up with solutions or answers to questions, humans are following a succession of connected thoughts, a path of reasoning that is unique for each individual. This train of thought is different from one individual to another and is based on the personal reality and experiences that the individual has lived. The talk shows how this train of thoughts can be defined and modeled for each individual or context. Based on past conversations and the use of different shapes of ideas and token stimulus alongside neural nets, we can classify responses, reason questions and come up with full sentences. The presentation takes a deep dive into the process of creating this shape of ideas and the different interpretations of each individual on the same topic.