Abstract-Performance improvement in both humans and artificial systems strongly relies in the ability of recognizing erroneous behavior or decisions. This paper, that builds upon previous studies on EEG error-related signals, presents a hybrid approach for human computer interaction that uses human gestures to send commands to a computer and exploits uses brain activity to provide implicit feedback about the recognition of such commands. Using a simple computer game as a case study, we show that EEG activity evoked by erroneous gesture recognition can be classified in single trials above random levels. Automatic artifact rejection techniques are used, taking into account that subjects are allowed to move during the experiment. Moreover, we present a simple adaptation mechanism, that uses the EEG signal to label newly acquired samples that can be use to re-calibrate the gesture recognition system in a supervised manner. Offline analysis show that, although the achieved EEG decoding accuracy is far from being perfect, these signals convey sufficient information to significantly improve the overall system performance. These studies have been typically performed during control of simulated devices where the subject is asked to limit its movements in order to avoid artifact contamination of the EEG signals. It is therefore, not yet clear whether this type of signals can be detected or exploited in less restrictive conditions. One of the goals of this work is to address precisely this issue. Moreover, the idea of hybrid systemsi.e. based on different communication channels-has been put forward recently as a way to improve the performance and usability of BCI systems and neuroprostheses [7]. We argue that the hybrid approach can exploit the brain activity to convey information about the subject cognitive and perceptual state, while control commands can be delivered using faster,