AI Expert Twin: Capturing Expert Cognition for Human-Centred, Practice-Based Learning

A team led by Annie Yuan at the University of Sydney has unveiled the AI Expert Twin framework, designed to capture and formalize the tacit knowledge embedded in expert practice. Published on arXiv, the paper addresses a critical gap in AI-driven education: while systems have advanced in personalization, learner modeling, and affective support, they rarely model the context-sensitive judgement and reasoning that experts use in practice-based domains. The framework represents expert cognition as a three-layer structure covering procedural actions, semantic concepts, and decision processes, while also incorporating value-laden preferences, trade-offs, and uncertainty.

To validate the approach, the team conducted a case study in a cultural heritage workshop, proving the framework's feasibility in a real-world setting. The AI Expert Twin is designed to be transferable across domains such as vocational education and creative industries, where hands-on, tacit knowledge is crucial. By embedding expert heuristics into AI while maintaining transparency and learner agency, the framework offers a novel path toward scalable, human-centred, practice-based learning. The researchers invite further study on ethical applications of AI in education, emphasizing the importance of preserving expert nuance without sacrificing learner autonomy.