Grounded · Multilingual · Action-Oriented
HealthBridge supports health decisions — it does not diagnose or replace a licensed provider.
Cue: "An engineered health navigation system — not a chatbot wrapper — where millions already are: WhatsApp."
Millions delay care — not from lack of access — but from fear, language barriers, and confusion.
Cue: "The problem isn't coverage — it's navigation. People freeze when they don't understand the system."
Not just immigrants — anyone uncertain or overwhelmed. WhatsApp already has 2B+ users. We meet them there.
Too much for Medicaid, too little for surprise bills. Needs clear cost guidance.
Multilingual triage, FQHC navigation, safe-access guidance regardless of status.
Newly off parents' insurance. Alone in medication and urgent care decisions.
No employer plan. Need fast triage before deciding if the ER is worth the bill.
Managing medications and follow-ups for elderly parents with complex needs.
Low health literacy, low system trust. Need a non-judgmental guide in their language.
Cue: "140M Americans have no family doctor they can call at 11pm. We built HealthBridge for all of them."
Every feature ends with a concrete action — not a wall of caveats.
Deterministic regex in 10+ languages. 911 directive — no LLM latency in the critical path.
Photo a pill bottle. Gemma extracts, FDA checks interactions, K2 explains clearly.
6-step flow via MedlinePlus + K2 reasoning. ER, urgent care, or wait at home?
ZIP-based HRSA/FQHC lookup. Nearest sliding-fee clinic in under 2 seconds.
Schedule reminders, reply "taken" to confirm. For caregivers and chronic patients.
Patient rights and protections for those afraid to seek care due to cost or status.
Cue: "Every feature is an action, not information. We guide to the next step — we don't just answer."
Cue: "From confusion to clinic referral in one conversation. No apps, no logins, no dead ends."
Cue: "Emergency? Deterministic. Document? Gemma. Safety? FDA. Guidance? K2. Each layer has one job."
Users send real health documents. Gemma converts visual data into structured JSON that downstream layers reason on — no manual re-typing.
Drug name, dose, route, frequency, prescriber. Normalized to RxCUI downstream.
OCR handles glare, rotation, partial occlusion via vision model.
Diagnosis codes, follow-up instructions, prescribed medications from hospital paperwork.
Numeric values + reference ranges; coverage decisions + appeal deadlines surfaced clearly.
Output JSON Schema
{ drugName: string,
dose: string,
frequency: string,
prescriber: string,
docType: enum,
confidence: 0–1 }
PDF Text Path
Direct text extraction — no vision cost. Regex-assisted parsing. Falls back to Gemma vision if text layer is absent.
Cue: "A user doesn't type drug names — they photograph the bottle. Gemma reads it. We normalize it. K2 reasons on it."
RxNorm Drug Normalization
rxnorm/rxcui lookup. Handles brand names, generics, misspellings.RxCUI — stable key for all downstream FDA queries.⚠ FAERS Adverse Event Signals
/drug/event.json?search=patient.drug.medicinalproductCue: "Real FDA data, normalized, scored, grounded — before we touch the reasoning layer."
K2 receives a structured context packet — grounded FDA data, extracted document fields, conversation memory — and produces one clear next step.
Reasoning Chain Example
01 — Context Loaded
Metformin + lisinopril + ibuprofen. Safety score: YELLOW. FAERS signal: 234 reports.
02 — Mechanism
NSAIDs reduce renal prostaglandins → impair ACE inhibitor efficacy → potential acute kidney injury.
03 — Output
🟡 Plain explanation. "Call your pharmacist — ask about an NSAID alternative."
Cue: "K2 doesn't just answer — it reasons. Grounded in real FDA data, it thinks before it speaks."
🔐 Session Security
🚦 Rate Limiting & Abuse
🚨 Emergency Override
⚖️ Clinical Guardrails
Cue: "Emergency detection is deterministic — it doesn't wait for an LLM."
Transport
Open-source WA multi-device library. QR pairing on /qr. Inbound router + media download.
AI Models
Unified inference for Gemma 3 27B (vision) and K2 Think V2 (reasoning). Provider-agnostic.
Data Sources
RxNorm, openFDA, FAERS, MedlinePlus, HRSA FQHC locator. All public — zero licensing cost.
Runtime
TypeScript throughout. Fastify high-throughput routing. Zod schema validation. Structured logging.
Deployment
Single-image Docker build. Hugging Face Spaces hosting. One-command deploy.
Key Routes
GET /health — WA connection statusGET /qr — device pairing QRPOST /send — outbound dispatchCue: "Every dependency is public or open-source. Zero licensing cost. One docker run and it's live on HF Spaces."
HealthBridge
Generic Health AI
Cue: "This isn't ChatGPT on WhatsApp. It's a layered clinical navigation system with real grounding and triage logic."
Grounded · Multilingual · Deterministic where it matters
HealthBridge is a decision-support tool. It does not diagnose, prescribe, or replace licensed medical providers.
Cue: "Message +1 (920) 489-5575 on WhatsApp. Ask about a medication. See why this is engineered navigation — not a chatbot."