AI-Care: A Conversational Agentic System for Task Coordination in Alzheimer's Disease Care

2026-05-08

AI Summary

This work proposes a voice-first natural language conversational agent designed to support individuals with Alzheimer’s disease, who often struggle to independently use conventional digital management tools due to cognitive impairments. Developed through a co-design approach, the system leverages LangGraph to implement a stateful dialogue flow that integrates intent recognition, context loading, slot filling, tool invocation, and response generation. To ensure safety and reduce cognitive load, it incorporates a caregiver verification mechanism and a controllable multi-turn clarification strategy. In an initial pilot study, four participants with mild-to-moderate Alzheimer’s disease unanimously rated the system as trustworthy, approachable, and effective, successfully completing everyday task coordination with its assistance.

Abstract

Individuals with Alzheimer's disease (AD) and Alzheimer's disease-related dementia (ADRD) experience memory and thinking changes that impact their ability to use digital daily management tools. For example, adding an event to a digital calendar requires multiple steps that may act as barriers to independent use for individuals with AD/ADRD. This paper presents AI-Care, a conversational agentic artificial intelligence (AI) layer built on top of a remote caregiving platform co-designed with people with AD/ADRD. AI-Care is designed to reduce the cognitive load on individuals with AD/ADRD when managing everyday tasks such as setting calendar reminders and organizing to-do lists through natural-language interaction with a voice-first chatbot. The system uses a LangGraph-based stateful orchestration approach in which each request passes through sanitization, intent classification, context loading, safety checks, deterministic slot collection, tool execution, and response composition. Safety-critical responses, particularly around medications and allergies, are grounded in caregiver-verified records rather than free-form model generation. The system does not make autonomous medical or treatment decisions. Incomplete or ambiguous requests are handled through controlled multi-turn clarification rather than silent failure or guessing. The system supports both typed and spoken input, with voice output through ElevenLabs text-to-speech. Longer responses are chunked before synthesis to avoid rushed playback. A preliminary pilot with four individuals with mild-to-moderate AD/ADRD showed that users found the system trustworthy, competent, and likable, and were able to complete the evaluated coordination tasks through conversation. We describe the design goals, system architecture, safety controls, and findings from this formative evaluation.

Problem

• Alzheimer's disease
• cognitive impairment
• digital daily management tools
• task coordination
• conversational AI

Innovation

• conversational agentic AI
• LangGraph orchestration
• cognitive load reduction
• safety-grounded generation
• multi-turn clarification