Design Principles for a Risk-Aware Conversational Agent in Digital Mental Health Information Access: The Case of Cognitive Theatre
TL;DR
Cognitive Theatre is developed, a risk-aware conversational agent informed by cognitive behavioural therapy and implemented through a controller-mediated role-decomposed architecture that escalated all 50 extreme-risk inputs and received higher response-level ratings than two baselines in AI-based assessment and a two-scenario human evaluation.
Abstract
This study investigates digital mental health as a high-stakes problem of conversational information access and interaction. Using Design Science Research Methodology, it develops Cognitive Theatre , a risk-aware conversational agent informed by cognitive behavioural therapy and implemented through a controller-mediated role-decomposed architecture. The system separates support into specialised roles for risk assessment, support selection, structured intervention, and user-facing delivery, and coordinates them through risk-aware routing. The artifact was evaluated through safety-routing, latency, AI-based comparative evaluation, and human comparative evaluation. Results show that, under controlled model-generated conditions, the architecture escalated all 50 extreme-risk inputs and received higher response-level ratings than two baselines in AI-based assessment and a two-scenario human evaluation. The study contributes design knowledge for building structured, inspectable, and context-sensitive conversational systems in sensitive domains, and extends research on human-centred conversational information access.