BACKGROUND Dementia causes a progressive loss of brain function which is often associated with a significant decline in autonomy to carry out activities of daily living, which can lead to functional impairments. Thanks to the current technological advances, resources aimed at cognitive stimulation have emerged. The importance of social robots is given by the ease with which they can promote interaction with the elder adults and the development of cognitive stimulation activities. OBJECTIVE The objectives of the present study were to assess the acceptability and level of interaction of the EBO social-care robot in day centre patients and to analyse whether the systematic viewing of the videos proposed in this study is a suitable tool for assessing the acceptability and interaction of the participants (day centre users) and the EBO robot of the Robolab laboratory. METHODS This study is a descriptive observational pilot study conducted on users of the AZTIDE social and health centre in Cáceres, Extremadura (Spain) who were beneficiaries of the cognitive therapy provided in the occupational therapy service. The inclusion criteria were women and men over 56 years old with a Minimental State Examination (MMSE) equal or over 21 (mild to moderate cognitive impairment). The "robot-participant" interactions took place in two individual interventions, lasting 10-15 min each, for each participant. The interactions replicated the Wizard of Oz technique where the human teleoperator acts as a robot without this being perceived by the elderly person. For this purpose, a user interface was displayed on the teleoperator's terminal and the commands were reproduced by the EBO robot. EBO is a robotic platform consisting of the following hardware for the experiment in question: display capable of generating emotions, RGB (red, green, blue) camera and basic navigation system. RESULTS A total of 6 users participated in the study. During the conversation between the participants and the EBO robot, eye contact was in all cases and in both interactions 100%, the attention paid by the participants to the robot is 10 out of 10 in 83.3%. All participants felt comfortable and calmed during the conversations (9 and 10 points out of 10). The values good and excellent were what the participants considered as regards conversational factors such as attentiveness, naturalness, meaningful conversation and feeling comfortable during both interactions with the EBO robot. CONCLUSIONS There was a high acceptability and level of interaction of the EBO social-care robot with the patients with mild to moderate cognitive impairment attending the day centre. Our results suggest that the systematic viewing of the videos proposed in this study provided enough data regarding the user-robot interaction for assessing the acceptability and interaction of the participants (day centre users) and the EBO robot of the Robolab laboratory. CLINICALTRIAL ClinicalTrials.gov registration identifier: NCT04896333