NeuroChat is a neuroadaptive AI tutor that combines generative AI with real-time EEG data to create a personalized, dynamic learning experience. Unlike traditional conversational AI, which relies on explicit user input, NeuroChat infers engagement levels directly from brain activity, modifying its responses to match the user's attention level, cognitive state, and learning preferences. When engagement dips, NeuroChat modifies its conversational strategy—adjusting response complexity, pacing, and level of interactivity—to re-engage the learner and maintain an optimal cognitive state.
NeuroChat is browser-based, lightweight, and designed for consumer-grade EEG headbands with dry electrodes, making neuroadaptive AI tutoring accessible beyond research environments. In our evaluation, NeuroChat increased cognitive and perceived engagement, as measured by EEG-based engagement indices and user evaluations, while immediate learning performance improvements were not observed. Those who preferred conversational, exploratory learning found it especially effective.
This project tackles one of the most pressing challenges in digital learning and AI-human interaction: how can an AI tutor move beyond static responses and actually “sense” user engagement? With AI-powered education on the rise, LLM-based tutoring systems are widely used, yet they remain passive, requiring the learner to manually communicate their engagement via prompt engineering. With NeuroChat, the system automatically adjusts, reducing cognitive effort and making interaction more fluid and human-like.
Beyond education, NeuroChat has implications for self-directed learners, knowledge workers, and accessibility applications. NeuroChat envisions a world where AI assistants don’t just respond to what we say—but how we think and feel in the moment.
We are interested in partnering with learning platforms to bridge the gap to enable generative AI to deliver truly personalized and customized support. Get in touch!