AI That Helps Us Help Each Other: A Proactive System for Scaffolding Mentor-Novice Collaboration in Entrepreneurship Coaching

Entrepreneurship requires navigating open-ended, ill-defined problems---identifying risks, challenging assumptions, and making strategic decisions under deep uncertainty. Novice founders often struggle with these metacognitive demands, while mentors face limited time and visibility to provide tailored support. We present a human-AI coaching system that combines a domain-specific cognitive model of entrepreneurial risk with a large language model (LLM) to proactively scaffold both novice and mentor thinking. The system surfaces personalized risks, poses diagnostic questions that challenge novices’ assumptions, and generates a coaching dashboard to help mentors plan more focused, emotionally attuned strategies. Critically, mentors can inspect and modify the underlying cognitive model, shaping the system’s logic to reflect their coaching expertise. Through a research-through-design process and an exploratory field deployment, we found the system improved meeting depth, intentionality, and focus---while also surfacing key tensions around trust, misdiagnosis, and expectations of AI. We contribute design principles for proactive AI systems that scaffold metacognition and human-human interaction in complex, high-uncertainty domains, offering implications for other ill-defined domains like healthcare, education, and knowledge work.