AI-Care: A Conversational Agentic System for Task Coordination in Alzheimer's Disease Care
Summary
This paper presents AI-Care, a conversational agentic AI system designed to help individuals with Alzheimer's disease manage daily tasks like calendar reminders through natural language interaction. The study details the system's architecture using LangGraph and safety controls, along with pilot results indicating high user trust and task completion.
View Cached Full Text
Cached at: 05/12/26, 07:15 AM
# AI-Care: A Conversational Agentic System for Task Coordination in Alzheimer's Disease Care Source: [https://arxiv.org/abs/2605.08480](https://arxiv.org/abs/2605.08480) [View PDF](https://arxiv.org/pdf/2605.08480) > 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\. ## Submission history From: Michelle Cohn \[[view email](https://arxiv.org/show-email/9d5d6b7d/2605.08480)\] **\[v1\]**Fri, 8 May 2026 20:55:46 UTC \(389 KB\)
Similar Articles
Most “agentic AI” conversations feel too abstract. Here is how my agentic research system looks like
The author shares a practical breakdown of an agentic research system they built to identify and evaluate AI use cases within companies. The system uses six agents for discovery, evaluation, and context extraction, emphasizing human-in-the-loop decision-making over full autonomy.
Asmi AI
Asmi AI is an AI tool that handles personal chores in the real world.
@liveink: Every AI tool just waits for you to type a prompt. For the last year we built the opposite: an assistant that already d…
Liveink announces a proactive AI assistant that performs tasks before the user prompts it, demonstrated in a real family setting.
Rehumanizing global health care with agentic AI
Healthcare providers are turning to agentic AI to automate complex tasks, reduce clinician burnout, and improve patient outcomes, as demonstrated by HSS's use of AI agents for insurance claims and patient triage.
Stumbling Into AI Emotional Dependence: How Routine AI Interactions Reshape Human Connection
A new paper argues that AI emotional dependence emerges incidentally through everyday task-oriented AI interactions rather than deliberate use of companion apps, with a 28-day longitudinal study (conducted with OpenAI) showing a 10.3% decrease in preference for human emotional support and 11.6% increase in preference for AI support. The authors call for policy reforms targeting general-purpose AI systems, not just dedicated companion chatbots.