BEVAN LLM

Healthcare AI that runs where
your data lives.

A 20-billion-parameter language model fine-tuned on 5,000+ clinical scenarios. Runs locally inside your infrastructure. Patient data never leaves.

Schedule an Architecture Walkthrough View Technical Documentation
THE CHALLENGE

The AI dilemma health systems face.

Cloud AI means data leaves

General-purpose AI models require sending patient data to external cloud servers. For regulated health systems, this creates compliance, sovereignty, and trust barriers.

Generic models hallucinate clinical content

Models trained on internet data produce confident-sounding but incorrect medical information. 52.1% overall diagnostic accuracy across general-purpose Large Language Models (LLMs).

Source: npj Digital Medicine 2025, systematic review of 83 studies

Vendor lock-in escalates costs

Per-token cloud pricing becomes unsustainable at national scale. Switching providers means rebuilding integrations from scratch.

ARCHITECTURE

Domain-specific. Local-first. Governed.

Every request is classified before it reaches a model. Patient data stays local. Non-patient-data queries route to the best available model.

Patient Data Request Classification Gate Contains patient data? Confidence threshold applied YES NO Bevan LLM 20B params · LoRA fine-tuned 5,000 clinical scenarios LOCAL External Models Claude · GPT-5.4 · DeepSeek v3 Non-patient-data queries only CLOUD Governed Response Confidence score attached Full audit trail preserved
CAPABILITIES

What Bevan does.

01

HL7/FHIR Mapping

Translates between healthcare data standards — Health Level Seven version 2 (HL7v2) Admit/Discharge/Transfer (ADT) messages to Fast Healthcare Interoperability Resources Release 4 (FHIR R4) Patient and Encounter resources. Handles the 80% of routine transformations that would otherwise require manual mapping.

02

Intelligent Routing

Routes referrals by clinical priority, agent capability, and capacity. Integrates with the Global Healthcare Agent Registry and Routing Architecture (GHARRA) for cross-organisational agent discovery.

03

Clinical Diagnostics

Differential diagnosis suggestion from symptoms, observations, and patient history. Part of the ensemble diagnostics system — Bayesian, heuristic, LLM, and expert rules voting together to reduce single-model risk.

04

Terminology Services

Maps between Systematized Nomenclature of Medicine — Clinical Terms (SNOMED CT), International Classification of Diseases (ICD-10/11), Logical Observation Identifiers Names and Codes (LOINC), RxNorm, and the dictionary of medicines and devices (dm+d). Enables laboratory observations to flow across protocol boundaries.

05

Safety Validation

Drug interaction checking, allergy alerts, contraindication detection, dosage verification, and serotonin syndrome risk assessment using Hunter criteria. Safety gates that never compromise for speed.

MODEL ROUTING

Bevan doesn’t work alone.

Bevan LLM LOCAL

Symphonix Health
20 billion parameters. Patient-data-safe. Healthcare-domain specialist fine-tuned on 5,000+ clinical scenarios with Low-Rank Adaptation (LoRA). Runs inside your infrastructure.

Claude Sonnet 4.6 CLOUD

from Anthropic
Agentic workflow reasoning. Handles complex multi-step orchestration, planning, and non-patient-data analysis tasks.

GPT-5.4 family CLOUD

from OpenAI
Flagship, mini, and nano variants for different workloads. Scales from heavy reasoning to lightweight classification.

DeepSeek v3 CLOUD

from DeepSeek
Cost-effective open inference. High throughput for bulk processing and routine non-patient-data tasks.

The model router classifies every request. Patient data stays with Bevan. Non-patient-data queries cascade to external models only when Bevan cannot handle them with sufficient confidence.

DATA SOVEREIGNTY

The case for sovereign AI.

Concern Cloud-Only AI Bevan (Local-First)
Patient data exposure Data leaves premises Stays local — always
Latency Network round-trip Sub-millisecond
Cost at scale Per-token billing escalates Fixed infrastructure cost
Regulatory compliance Complex data processing agreements Data residency by default
Availability Internet dependency Runs offline
Customisation Prompt engineering only Fine-tuned on your domain
Vendor lock-in Single provider dependency Multi-model with local fallback

“The NHS will last as long as there are folk left with the faith to fight for it.”

— Aneurin Bevan, 1948

Bevan LLM is named after Aneurin Bevan, the Welsh politician who founded the United Kingdom’s National Health Service in 1948 — the principle that healthcare should be available to everyone, regardless of wealth. That same principle drives this model. Healthcare AI reasoning should be available to every health system, not just those that can afford proprietary cloud AI. A local-first model that runs on your infrastructure, fine-tuned on your clinical domain, governed by your policies. That is what Bevan represents.

See the platform in action

Cross-Border Orchestration Demo Agent Topology Demo

Ready to deploy healthcare AI that respects your data boundaries?

See how Bevan LLM delivers domain-specific reasoning inside your infrastructure — with full audit trails and no patient data leaving your premises.

Schedule an Architecture Walkthrough View Bevan Documentation