Abstract: A system and method for AI-assisted conversation utilize a biosensor to receive biosignals, which are analyzed by the perception engine. The engine generates context tags and text descriptions from multimodal sensory inputs and biosignal analysis. This information is then used by the conversation engine, along with memory engine data (conversation history, biographical background, keywords), to generate prompts for a language model. These prompts are displayed to a user through a computing device that presents various conversation features like communication history, context data, and selected content. The system enables interactive AI-assisted conversations between humans and machines or other humans.

Abstract: There are disclosed herein systems and methods for human agency support and facilitation through an integrated use of context information, historical work product, biosensors, explicit user input and a generative AI or generalist agent. The system comprises input means, tokenization, a generative AI or generalist agent and an output stage capable of enacting agency on a user's behalf using output tokens from the language model.

Abstract: An electrode assembly and a system including it are disclosed. The electrode assembly includes an electrode body with arc rail(s) attached to and extending from the electrode body. The arc rail(s) include at least one sensing element for sensing or stimulating the state of a particular property of a selected subject area when applied by the arc rail to that area. The arc rail is so disposed in relation to the electrode body as to be disposed at a non-perpendicular angle to the subject area when the electrode assembly is applied to the selected subject area. The system includes an analog front end (AFE) configured to receive output signals from at least one electrode assembly and transmit the output signals to a digital module for processing. The system also includes an accessory strap with sockets to receive electrode assemblies and deliver their outputs to the AFE.

Abstract: A method and system are disclosed using steady-state motion visual evoked potential stimuli in an augmented reality environment. Requested stimuli data are received from a user application on a smart device. Sensor data and other context data are also received, where other context data includes data that is un-sensed. The requested stimuli data are transformed into modified stimuli based on the sensor data, and the other context data. Modified stimuli and environmental stimuli are presented to the user with a rendering device configured to mix the modified stimuli and the environmental stimuli, thereby resulting in rendered stimuli. Biosignals generated in response to the rendered stimuli are received from the user to a wearable biosignal sensing device. Received biosignals are classified based on the modified stimuli, resulting in a classified selection, which is returned to the user application.