Ambient Intelligence (AmI, shortly) gathers best results from three key technologies, Ubiquitous Computing, Ubiquitous Communication, and Intelligent User Friendly Interfaces.The functional and spatial distribution of tasks is a natural thrust to employ multi-agent paradigm to design and implement AmI environments. Two critical issues, common in most of applications, are (1) how to detect in a general and efficient way context from sensors and (2) how to process contextual information in order to improve the functionality of services. Inthis work we experiment a framework where hybrid techniques (distributed fuzzy control, mobile agents, fuzzy rules induction algorithms) are mixed to gain flexibility and uniformity