Purpose -Taking into account the importance of e-commerce and the current applications of AI techniques in this area, this research aims to adequate the design of a multi-agent system for the provisioning of e-services in u-commerce environments. This proposal is centred on the methods of evaluation in a u-e-commerce environment. Design/methodology/approach -The multi-agent systems (MAS) approach is based on an MAS model developed for AmI that has been redesigned to support u-commerce. The use of a recommendation system, previously developed by the research group, is suggested for this MAS. The methodological proposal centres on the evaluation of this type of system. Findings -The evaluation of this type of system is the principal problem of current research. Therefore, this is the main contribution of the paper. Research limitations/implications -The different evaluation methods that are proposed, whether qualitative or quantitative, offer the possibility of measuring the added value that the context can give to the use of e-services in different domains of application. Qualitative evaluation should consider the customer as a central piece in the system. In addition, quantitative methods should objectively evaluate the contribution of context to the application. Practical implications -At present, there is no single method for evaluating the benefits of different u-commerce systems, so a new method needs to be found based on these techniques. Originality/value -The research proposes an MAS designed for u-commerce domains, analyzes the capacity of trust management techniques in this environment, and proposes several evaluation methods to show the benefits of context information in the use of e-services. Several real developments are described to show the different applications of MAS in u-commerce and how evaluation is carried out.