Simulation of retail space is a growing topic in the multi-agent systems community. Those systems vary depending on many issues, such as the type of store, or type of behaviour. The kind of issue that is wished to be simulated, or the type of data used to build the simulation, are other subjects of variations. Our ambition is to develop a simulator using a generic model, based on real data easy to collect. In this paper, we focus on the agent model. We develop it and make some experiments to test it.