The authors built a voice-first chatbot for people with Alzheimer's to manage calendars and to-do lists through natural conversation, layered on top of a caregiving platform. The system uses a state-machine approach (LangGraph) that sanitizes input, classifies intent, loads context, checks safety constraints, collects missing information through follow-up questions, executes actions, and composes responses. Safety-critical facts like medications come from caregiver-verified records, not model generation, and the system never makes autonomous medical decisions. A pilot with four users showed they found it trustworthy and could complete coordination tasks by talking.
Main takeaways:
- Designed to reduce cognitive load for people with memory/thinking impairments by handling multi-step tasks (calendar, reminders, lists) through simple conversation
- Uses a deterministic state machine for orchestration: every request goes through sanitization, intent classification, context loading, safety checks, slot-filling dialogue, tool execution, and response generation
- Safety-critical information (medications, allergies) is retrieved from caregiver-verified records rather than generated by the language model
- Handles ambiguous or incomplete requests through controlled multi-turn clarification instead of guessing or failing silently
- Preliminary user testing (n=4, mild-to-moderate Alzheimer's) found the system trustworthy, competent, and usable for coordination tasks