The paper presents a distributed intelligence-based system concept for modeling and self-optimizing the production of flat steel products. The concept is implemented through a multi-agent system approach. In particular, three types of autonomous agents are modelled, each playing a different role in the steel production chain. The agents are designed in order to take autonomous decisions based on their current and target state, to adapt the production scheduling through optimization algorithms and communicating each other to react on unforeseen interruptions and disturbances. The approach is designed for the steel coil coating manufacturing but can be easily readapted to any brown-field scenario.