The project that taught a 26-year-old what conviction actually costs

Singapore, 2014. A wearable for autism — built not because anyone asked for it, but because the clinical system had a gap that no one was filling. Real-time support for individuals with sensory dysregulation, in the moment, in their daily life. Not medication. Not a scheduled therapy session. A continuous bridge between physiological trigger and self-regulation response.

The project was called Heartware. The device — Kerbie — combined ECG-based emotion classification, environmental context capture, a patient-facing app, and a caregiver dashboard. Published research backed the approach. A development grant validated it. A startup studio showed interest.

Three months later it was over. The co-founding team broke apart before the prototype was finished. The IP stayed. The conviction went underground for years.

But it never disappeared. The architecture designed in that Singapore hackathon room — persistent monitoring, real-time feedback, patient agency alongside caregiver visibility — is structurally identical to what the largest health platforms in the world are now racing to build.

Early. Not wrong.

Tomorrow: the full story — the design, the breakdown, the twelve years between, and what the rebuild would look like now.