Accessibility settings

Published on in Vol 8 (2025)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/76489, first published .
Child-friendly robot on a table interacting with a person

A Hybrid Rule- and Large Language Model–Based Embodied Voice Assistant (GRACE) for Cognitive Stimulation in Older Adults: Usability Study Assessing Technical Feasibility, Technology Acceptance, and Working Alliance

A Hybrid Rule- and Large Language Model–Based Embodied Voice Assistant (GRACE) for Cognitive Stimulation in Older Adults: Usability Study Assessing Technical Feasibility, Technology Acceptance, and Working Alliance

Journals

  1. Walliser F, Biller-Andorno N, Kowatsch T, Vinay R. Evaluating the GRACE voice assistant for dementia care among caregivers and healthcare professionals: An interview study. DIGITAL HEALTH 2026;12 View
  2. Shenoi A, Li T, Jabir A, Pitkethly A, Fleisch E, Kowatsch T, Mair J. Structured Large Language Model Workflows for Motivational Interviewing in Health Behavior Change: Proof-of-Concept Study. JMIR Formative Research 2026;10:e94036 View

Conference Proceedings

  1. Moser F, Vinay R, Kowatsch T. Proceedings of the 8th ACM Conference on Conversational User Interfaces. STELLA: An Open-Source Platform for Auditable Voice-First Conversational Health Coaching Agents View
  2. Li Y, Saragih I, Fick D, Sundar S, Abdullah S. Proceedings of the 8th ACM Conference on Conversational User Interfaces. A Real-Time Voice Agent for Delivering Individual Cognitive Stimulation Therapy to Persons Living with Dementia View