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
The results suggest that embodied rule-based and LLM VAs like GRACE are feasible and well-received tools for delivering cognitive interventions to older adults. Future iterations will incorporate feedback and extend testing to individuals at risk for dementia.
Authors
- Екатерина Уэтова (ORCID: https://orcid.org/0009-0009-9605-9616)
- Rasita Vinay (ORCID: https://orcid.org/0000-0002-0490-5697)
- Tobias Kowatsch (ORCID: https://orcid.org/0000-0001-5939-4145)
- Nikola Biller‐Andorno (ORCID: https://orcid.org/0000-0001-7661-1324)
- Nora Camilla Tommila (ORCID: https://orcid.org/0009-0002-8926-7184)
Institutions
- University of Zurich (CH)
- University of St.Gallen (CH)
- ETH Zurich (CH)
- Technological University Dublin (IE)
Publication Details
- Journal
- JMIR Aging
- Published
- 2025-11-10
- DOI
- https://doi.org/10.2196/76489
- Citations
- 1
- Primary Topic
- AI in Service Interactions
- Type
- article
- Field-Weighted Citation Impact
- 2.48