DailyDawn — eldercare check-ins on Ring

Inspiration

What it does

How we built it

Challenges we ran into

Accomplishments that we're proud of

What we learned

What's next for DailyDawn — eldercare check-ins on Ring

Inspiration

We noticed that many families worry about the safety of aging parents living alone but find constant phone calls intrusive. We wanted to transform the Ring ecosystem from a simple security tool into a proactive caregiving assistant. Our goal was to create DailyDawn to bridge the gap between hardware sensing and intelligent AI interaction.

What it does

DailyDawn uses Ring motion sensors to trigger gentle check-ins throughout the day. When no movement is detected, an AI agent initiates a conversation to verify the user's well-being and medication adherence. If the system detects distress or a lack of activity, it alerts family members immediately through a custom dashboard.

How we built it

We hosted our backend logic on aws-app-runner to ensure scalable and reliable deployment. We used amazon-bedrock to power the natural language processing and crewai to manage complex caregiving workflows. The integration relies on amazon-ring APIs to fetch event data and trigger the DailyDawn logic.

Challenges we ran into

Mapping asynchronous event data from Ring to a stateful AI conversation was difficult to time right initially. We also had to refine the crewai agents to ensure the tone remained empathetic and helpful rather than robotic. Balancing the sensitivity of alerts to avoid false positives required multiple iterations of logic.

Accomplishments that we're proud of

We are proud of how seamlessly we integrated crewai agents with real-time Ring data. The AI-driven check flow feels natural and responsive, which was a major technical milestone for us. Successfully deploying on aws-app-runner handled our concurrent requests with minimal latency.

What we learned

We learned a lot about orchestrating multi-agent systems using crewai for specific healthcare use cases. We also gained deep insights into prompt engineering for amazon-bedrock to ensure accessibility for an elderly user base.

What's next for DailyDawn

We plan to integrate voice-based interactions directly through the Ring-enabled smart speakers. We also want to expand our agent logic to include predictive analytics for identifying potential health issues before they become emergencies.

Built With

• amazon-bedrock
• amazon-ring
• aws-app-runner
• crewai
• eldercare
• python