# Overview Our algorithm for Mental Commands works using pattern recognition and requires that you train at least one Neutral state and one Command state. The system learns to recognize the patterns of brain activity that are related to your Command state compared to your Neutral state. Though you can start using a profile after training a Command only one time, we highly recommend you do repeat trainings for each Command and for your Neutral state. The more training that you do, the better the system will be able to detect the pattern of brain activity associated with your Command thought AND the better you will get at learning how to recreate that thought in your mind. We have associated the the Mental Commands inside EmotivBCI with the movements of a cube including Push, Pull, Left, Right, Up, Down, Rotate, Disappear. This way you can practice using your command inside the app in [Live mode](/emotivbci/mental-commands/live-mode.md) and get feedback that it is working or not. Outside of the application, however, you can associate these commands to any digital output you choose, even if they are not related to the movement of an object. For example, your “Up” command can be used to turn on the smart lights in your home using Node-RED. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://emotiv.gitbook.io/emotivbci/mental-commands/overview.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.