The main purpose of the ENRICHME European project is to develop a socially assistive robot that can help the elderly, adapt to their needs, and has a natural behavior. In this paper, we present some of the lessons learnt from the first interaction between the robot and two elderly people from one partner care facility (LACE Housing Ltd, UK). The robot interacted with the two participants for almost one hour. A tremendous amount of sensory data was recorded from the multi-sensory system (i.e., audio data, RGB-D data, thermal images, and the data from the skeleton tracker) for better understanding the interaction, the needs, the reactions of the users, and the context. This data was processed offline. Before the interaction between the two elderly residents and the robot, a demo was shown to all the residents of the facility. The reactions of the residents were positive and they found the robot useful. The first lessons learnt from this interaction between Kompa¨ıKompa¨ı robot and the elderly are reported.