This paper formulates the problem of service selection. It reformulates two tradi- tional recommender approaches for service selection and proposes a new agent-based approach in which agents cooperate to evaluate service providers. In this approach, the agents rate each other, and autonomously decide howmuch to weigh each other's recommendations. The underlying algorithm with which the agents reason is devel- oped in the context of a concept lattice, which enables nding relevant agents. Since large service selection datasets do not yet exist, for the purposes of eval- uation, we reformulate the well-known product evaluations dataset MovieLens as a services dataset. We use it to compare the various approaches. Despite limiting the ow of information, the proposed approach compares well with the existing approaches in terms of some accuracy metrics de ned within.