Reco
Recovery starts in the mind.
The hardest part of ACL recovery isn't the knee. It's the isolation, the repetition, the slow erosion of belief. We built something to fight that — in 48 hours.
Meet Reco.
Every screen designed around one rule: warm, approachable, and completely free of clinical anxiety.
Three needs. One system.
RECO is built on Self-Determination Theory. Three psychological needs — autonomy, competence, relatedness — drive sustained motivation. RECO addresses all three, simultaneously.
VITA AI Companion
Grounded in PubMed research. Evidence-based guidance on rehabilitation and nutrition — from a companion who feels like a friend, not a database.
Smartphone IMU
The phone's built-in sensors measure leg angle, speed, and range of motion. Accurate form feedback, no wearables required.
iOS Widgets
Recovery day count and daily check-ins, right on the home screen. A quiet reminder that progress is happening.
48 hours. One honest constraint.
Built from the inside.
One teammate was actively recovering from an ACL tear. We didn't need user interviews. We had the real thing — daily frustrations, real stakes, no hypotheticals.
AI handled the boilerplate. We handled the thinking.
Offloading syntax to AI freed us to focus entirely on what mattered: medical constraints, product strategy, and the user.
No hierarchy. Just speed.
Strangers on day one. We skipped the org chart and went straight to building — concept to shipped iOS prototype before the deadline.
The hardest part isn't the knee.
Rehabilitation is a psychological battle as much as a physical one. 41.8% of athletes experience anxiety and depression during recovery — and both directly undermine the daily exercises that determine outcomes.
"The biggest challenge after ACL surgery isn't just physical — it's psychological."
Caumeil B, et al. Reinjury Anxiety and Return to Sport After ACL Reconstruction: Cluster Analysis and Prospective Study Among 162 Athletes.
My role architecture to screen.
I owned the full stack — API logic, visual language, and frontend execution. Prompt engineering for medical safety, user flows in Figma, core screens in Swift.
Constraining the LLM
Integrated GPT-4o-mini with strict system prompts. VITA stays in its lane — rehabilitation and nutrition only. Medical hallucination risks, eliminated.
PubMed Medical Pipeline
Connected VITA directly to NCBI Entrez PubMed. Every answer traces back to a peer-reviewed paper, not generic internet data.
Protecting Credentials
Supabase server-side encryption for all API keys. OpenAI and PubMed credentials never touch the frontend bundle.
Frontend & Interaction
Core screens — chat, visualization widgets — built in Swift and React Native. Functional and shipped within the 48-hour window.
Visual Design (Figma)
Full user flow and visual language defined in Figma. The goal: an interface that feels safe to someone in pain.
What we built with.
| AI MODEL | ChatGPT-4o-mini | OpenAI API |
| MEDICAL DATA | NCBI Entrez PubMed Database | MED-API |
| SECURITY | Supabase Server-side Key Storage | Encryption |
| PLATFORM | iOS Mobile Application | Swift / React Native |
| DESIGN TOOL | Figma (Role: User Flow & Visual System) | Figma |
| FRAMEWORK | Self-Determination Theory (SDT) | Psychology |
"A hackathon stops you from over-designing and starts you building. It proved that empathy, combined with the right AI, can solve real problems, fast."