Can we accelerate the process of molecular discovery by combining automation with machine learning tools? Rapid discovery of novel molecules with tailored properties is crucial for the chemical, petrochemical, and pharmaceutical industries. Autonomous optimization of chemical reactions is one of fundamental tasks in self-driving labs. Here, I will present on how Kebotix ChemOS™ orchestrates and optimizes chemical reactions in real world scenarios. In addition to state-of-the-art optimization algorithms implemented, ChemOS™ integrates lab instruments, coordinates the reaction workflows, and collects data in an AI-processable format.