Socratic: Enhancing Human Teamwork via AI-enabled Coaching

2025-02-24

AI Summary

In mission-critical domains such as healthcare and emergency response, the scarcity of expert team coaches impedes real-time collaborative effectiveness. To address this, we propose the first AI-powered real-time team coaching paradigm explicitly designed for task execution processes. Methodologically, we introduce a lightweight framework grounded in shared understanding discrepancy detection, integrating multimodal behavioral sensing, team cognitive state modeling, an intervention decision engine, and a human–AI trust calibration mechanism—enabling minimal, cognitively aligned interventions. This work bridges a critical gap in human–AI collaboration research by formalizing *process-oriented* coaching. In a two-person collaborative task study, our approach significantly improved team performance (p < 0.01), reduced intervention frequency by 62%, and achieved 92% participant endorsement of its credibility and practical utility.

Technology Category

• Humans and AI: Human-AI Collaboration / Human-AI Teaming
• Multiagent Systems: Teamwork
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Coaches are vital for effective collaboration, but cost and resource constraints often limit their availability during real-world tasks. This limitation poses serious challenges in life-critical domains that rely on effective teamwork, such as healthcare and disaster response. To address this gap, we propose and realize an innovative application of AI: task-time team coaching. Specifically, we introduce Socratic, a novel AI system that complements human coaches by providing real-time guidance during task execution. Socratic monitors team behavior, detects misalignments in team members' shared understanding, and delivers automated interventions to improve team performance. We validated Socratic through two human subject experiments involving dyadic collaboration. The results demonstrate that the system significantly enhances team performance with minimal interventions. Participants also perceived Socratic as helpful and trustworthy, supporting its potential for adoption. Our findings also suggest promising directions both for AI research and its practical applications to enhance human teamwork.

Problem

• AI enhances team coaching
• Real-time team behavior monitoring
• Improves critical task performance

Innovation

• AI-enabled real-time coaching
• monitors and detects team misalignments
• automated interventions improve performance