Agentic AI adapts personalized sleep reminders using daily data
An Agentic Just-in-Time Adaptive Intervention System for Personalized Sleep Support: Proof-of-Concept Study with N of 1 Data
Human-Computer InteractionArtificial Intelligence
Summary
Getting better sleep often means changing habits, but adjusting advice to each person's needs can be tricky. The authors created a smart system that looks at 30 days of a person's sleep and daily activities to find patterns. This system then creates or updates helpful reminders about sleep habits automatically and learns as it goes. It works under human supervision and can be expanded to help with other health habits too.
What this means in practice
- •For health technology developers: Build smart home systems that personalize sleep habit reminders based on user data to improve intervention relevance and flexibility.
- •For digital health platform teams: Integrate AI agents that adapt behavioral interventions dynamically to enhance patient support beyond fixed rule sets.
Tested on one dataset.
Authors
Nick Rezaee, Chelsea Boccagno
Abstract
Background: Just-in-time adaptive interventions (JITAIs) can use behavioral data to adapt support to changing contexts, but many rely on predefined rules and manual configuration. Objective: We developed a proof-of-concept sleep JITAI using an AI agent to review personal data, evaluate reminders, adapt interventions, and record decisions for human review. Methods: Running in Home Assistant on a configurable schedule, the agent follows a reusable skill file to review 30 days of sleep and behavioral data, including physical activity, smartphone use, and bedtime routines, to identify patterns and create or update automated reminders. Results: Initial runs demonstrated technical feasibility, successfully completing data review and intervention decisions while limiting reminders to three per day and saving decision records. Conclusions: Agentic AI may enable flexible, adaptive sleep JITAIs. The architecture supports future comparison with fixed or rulebased interventions, requires human oversight, and could extend to other health behaviors.