CareLink
Voice-first elder care companion with real-time emotion recognition. Shifts support from reactive crisis response to proactive, continuous monitoring.
The Problem
Elder care is reactive. Problems surface only after a crisis. Caregivers are overwhelmed, disconnected from day-to-day reality. Elderly users often can't or won't type — they need voice, and the system needs to understand not just what they say but how they feel.
Voice AI & Emotion Recognition
The core interaction is voice-first through ElevenLabs integration. The dialogue agent runs a Listener → Emotion → Planner → Coach pipeline. The Emotion stage classifies emotional content before any response is planned — the system doesn't just hear "I'm fine," it detects when "I'm fine" means the opposite.
A mind-behavior engine tracks emotional, cognitive, social, and routine patterns over time — longitudinal trends, not just snapshots. A caregiver gets alerted not because someone had one bad day, but because the system detected a three-week downward trend.
Architecture
Three agent layers: dialogue agent handles voice + emotion-aware responses. Coach agent generates personalized care plans. Safety agent evaluates incidents in real time and fires caregiver alerts. An event bus with persistent backlog ensures no signal is lost.
The Result
60 commits, working full-stack system with voice interface, emotion-aware dialogue, and caregiver alerting. Tested with real safety scenarios.
My Role
System architect. Designed the three-layer agent topology, the emotion recognition pipeline, and the event-driven architecture. Built the safety agent, memory management layer, and the developer playground frontend.