SAGE: Sensor-Augmented Grounding Engine for LLM-Powered Sleep Care Agent

TL;DR

SAGE is a sensor-augmented engine that enhances LLM-powered sleep care agents by grounding data, enabling personalized, trustworthy, and actionable insights through selective monitoring and natural language queries.

Contribution

It introduces a novel data normalization and querying framework that grounds LLM responses in personal sensor data for sleep care.

Findings

Supports meaningful deviation detection to reduce alert fatigue.

Enables natural language queries grounded in precise sensor data.

Enhances personalization and traceability in sleep health interventions.

Abstract

Sleep is vital for health, yet access to data alone does not guarantee improvement. While wearables and health apps enable tracking, users face a "Data-Action Gap," struggling to interpret metrics and translate them into action. Current interventions fail to bridge this: static dashboards lack context, rule-based agents rely on rigid scripts, and LLM-agents lack grounding in personal data, causing trust issues. We propose SAGE (Sensor-Augmented Grounding Engine) for an LLM-powered sleep care agent. SAGE normalizes continuous sleep, physiological, and activity data from the sensors into a queryable time-series layer. It supports (1) selective system-initiated monitoring that triggers notifications only upon detecting meaningful deviations against personal baselines to reduce alert fatigue, and (2) user-initiated Q&A where natural language is translated into executable database queries. By ensuring responses are grounded in precise period, comparison, and metric data, SAGE aims to enhance personalization, traceability, and trust, articulating a novel design space for evidence-based messaging in sleep care.