HeartBridge

The Problem

Cardiac rehab materially improves outcomes after a heart event, but 75% of eligible patients never attend a single session. The reasons aren't medical. They're logistical, emotional, and motivational: transportation barriers, anxiety about returning to exercise, lack of ongoing encouragement between appointments, and no visibility into recovery progress outside a clinical setting.

Existing cardiac rehab programs are facility-dependent, appointment-heavy, and offer little support between visits. For the majority of patients who don't show up, there's nothing bridging the gap between discharge and recovery.

The Insight

The participation problem isn't about information. Patients know rehab matters. The failure is structural: the current model requires people to come to the program instead of bringing the program to the person. A warmer, voice-driven companion that checks in, coaches through exercises, and keeps a care circle informed could reach the 75% that traditional programs miss entirely.

The Solution

HeartBridge is a cardiac rehab companion that combines voice coaching, daily progress tracking, and care-circle support into a single recovery experience. Patients get a personal voice coach that guides them through exercises, checks in on how they're feeling, and surfaces their progress to family members and clinicians. The goal is to make rehab feel less clinical and more like having someone in your corner.

How It Works

1. Step 01

   Voice-guided sessions

   An ElevenLabs-powered voice coach walks patients through exercises, adjusting encouragement based on how they're responding.

2. Step 02

   Daily check-ins

   Short, conversational check-ins capture how the patient is feeling physically and emotionally, tracking recovery trends over time.

3. Step 03

   Progress visibility

   A dashboard shows recovery milestones, session history, and trends so patients can see that the work is adding up.

4. Step 04

   Care circle

   Family members and clinicians get visibility into the patient's recovery without requiring the patient to report manually.

Architecture

Build Process

HeartBridge was built in a single day at the Pulse Foundry AI NYC Healthcare hackathon on March 29, 2026. I was placed on a randomly assigned team of 6 strangers. I designed roughly 80% of the product, led the overall build, and presented the winning demo.

The build started with a Lovable MVP to get the UI shell up fast. I then combined that repo with health-domain work from a prior project (VitalMed) in Factory AI using Opus 4.6, re-architecting from a README implementation plan. During the build, I reviewed and merged 5 teammate PRs using Amp smart mode to keep the codebase consistent.

The result was a working prototype with voice coaching, progress tracking, and a care-circle dashboard, all presented live to the judges.

Key Design Decisions

• Voice-first over text-first: Cardiac rehab patients skew older and are recovering physically. A voice interface is lower friction than typing and feels more like a real coach checking in.
• Care circle over solo tracking: Recovery doesn't happen in isolation. Giving family members and clinicians visibility creates a support network without burdening the patient with manual updates.
• Warmth over clinical precision: The tone is encouraging, not medical. HeartBridge isn't replacing a cardiologist. It's filling the motivational gap between appointments.
• Lovable for speed, Factory for structure: Starting with Lovable got a visual prototype up in hours. Moving to Factory AI for the re-architecture let us ship something structurally sound by demo time.
• Amp for team coordination: With 6 strangers submitting code simultaneously, using Amp smart mode for PR review and merging kept the repo from turning into chaos.

Outcomes

• 1st place at the Pulse Foundry AI NYC Healthcare hackathon.

What It Demonstrates

• Hackathon leadership: Designed 80% of the product and led the build with a team of strangers under extreme time pressure.
• Multi-tool orchestration: Combined Lovable, Factory AI, Amp, Claude, and ElevenLabs into a coherent build pipeline in one day.
• Healthcare product judgment: The product was shaped around a real participation gap backed by clinical data, not a generic "AI for health" concept.
• Team coordination under pressure: Managed 5 teammate PRs through Amp smart mode while leading the core architecture.