Recommender systems are considered as useful software that helps users in screening and evaluating products. The fact that users do not know how these systems make decisions leads to an information asymmetry. Thus, users need to trust if they want to take over systems’ recommendations. Applying social interfaces has been suggested as helpful extensions of recommender systems to increase trust. These are called (Social) Recommendation Agents. While many articles and implementations can be found in the field of e-commerce, we believe that Recommendation Agents can be applied to other contexts, too. However, a structured evaluation of contexts and design dimensions for Recommendation Agents is lacking. In this study, first, we give an overview of design dimensions for Recommendation Agents. Second, we explore previous research on trust and Recommendation Agents by means of a structured literature review. Finally, based on the resulting overview, we highlight three major areas for future research.