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

TL;DR

This paper introduces a proactive human-AI coaching system that enhances entrepreneurial mentoring by supporting metacognition and collaboration, leading to more focused and emotionally attuned meetings in complex, uncertain domains.

Contribution

It presents a novel AI system combining domain-specific cognitive modeling with LLMs to proactively scaffold entrepreneurial coaching and allows mentors to customize the system's logic.

Findings

Supported novice metacognition and strategic planning.

Improved meeting depth, focus, and emotional attunement.

Identified trust and misdiagnosis challenges in AI-human collaboration.

Abstract

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 proactively poses diagnostic questions that challenge novices' thinking and helps both novices and mentors plan for more focused and emotionally attuned meetings. Critically, mentors can inspect and modify the underlying cognitive model, shaping the logic of the system to reflect their evolving needs. Through an exploratory field deployment, we found that using the system supported novice metacognition, helped mentors plan emotionally attuned strategies, and improved meeting depth, intentionality, and focus--while also surfaced key tensions around trust, misdiagnosis, and expectations of AI. We contribute design principles for proactive AI systems that scaffold metacognition and human-human collaboration in complex, ill-defined domains, offering implications for similar domains like healthcare, education, and knowledge work.