All case studies
HealthTech / AI Triage

Geen.ai

Up to 50% cost reduction in health-service navigation
2025

The Problem

Healthcare navigation is broken. In Italy alone, 5.8 million people gave up on medical visits in 2024 due to waiting lists or costs, nearly 10% of the population. Three in ten hospitalizations could have been avoided with better routing to territorial services. And companies watch only 5% of corporate welfare budgets get used for health and prevention.

The gap isn't a lack of services. It's that people can't find the right one. They describe symptoms and needs in natural language; the system offers them a directory.

The Product

Geen.ai is an AI triage and orientation layer that interprets natural language and guides each person to the most appropriate health service, which means less wasted time, fewer dead-end attempts, and lower costs. For companies, health benefits become real value through targeted utilization. For healthcare organizations, booking requests become more appropriate access with less load on clinical staff.

The Engineering

Triage AI in healthcare is a guardrails-first problem: the system must understand messy human language about symptoms and needs, route with high confidence, and know exactly when to hand off to a human. We worked on the AI layer's engineering: the natural-language understanding and routing infrastructure where a wrong answer isn't a bad UX moment but a health decision.

How the triage engine actually works

Every request runs through the same guardrails-first pipeline: the LLM interprets messy natural language, a GraphRAG knowledge graph routes to the right subspecialty, then deterministic filters rank real, reachable specialists — no diagnosis, no PII stored.

Describe

User describes symptoms in natural language via the chat widget, with sex and age.

KB match

Backend searches the knowledge base for rules matching symptom, gender, and age band.

LLM analysis

The LLM returns primary and secondary specialty, urgency, red flags, and gender-medicine notes.

GraphRAG route

Neo4j traverses Symptom → Subspecialty → Physician using knowledge extracted from PubMed.

Filter & rank candidates
Insurance

Filter physicians by tenant coverage — SSN, UniSalute, Metasalute, FASI, and more.

Proximity

Rank by geographic distance from the patient's coordinates.

Red flags

Urgent symptoms escalate and alert the project owner.

Routed to the right specialist

The person is guided to the most appropriate service — anonymized log stored, no diagnosis, no PII.

Outcomes

  • Natural-language triage routing people to the most appropriate care service
  • Up to 50% cost reduction for companies activating the navigation layer
  • More appropriate access and reduced load on clinical staff for healthcare providers
  • Trusted by enterprises and public healthcare organizations in Italy