MADS is a project developed by AI Flow Solutions that enables users to systematically perform a data science pipeline with just two inputs: a problem description and a CSV file containing data. The MADS framework orchestrates a multi-agent system that generates predictions, produces a detailed report on the data, and trains a machine learning model. The next phase of this project will introduce complexity by incorporating reinforcement learning to enhance the performance of each agent. Currently, this project is being developed on top of the Autogen framework.