An air-gapped LLM assistant for claims handlers.

Claims and onboarding AI, zero external egress.

We partnered with an innovative insurance provider to build a fully self-hosted AI assistant for claims processing and customer onboarding. The client operated under strict data protection requirements: customer data including health information, financial details, and personal identifiers could not leave their infrastructure under any circumstances.

Cloud-hosted LLM APIs were categorically excluded. Our mandate was to deliver production-grade AI capabilities with complete data sovereignty, GDPR Article 28 processor compliance, and audit-ready documentation.

Absolute data sovereignty, regulatory explainability.

• Absolute data sovereignty: Insurance claims contain special category data under GDPR (health information) and financial PII. No data could be transmitted to external APIs, requiring fully on-premises model inference with no external dependencies.
• Regulatory explainability: FCA conduct rules require that customer-facing communications are clear, fair, and not misleading. AI-generated responses needed documented reasoning, source citations, and human oversight for edge cases.
• High manual workload: Claims handlers spent 80% of their time on repetitive document extraction, data entry, and standard response generation, creating processing backlogs and customer frustration.
• Integration complexity: The solution needed to integrate with legacy CRM, document management, and policy administration systems, many with limited API capabilities.

On-prem Llama, RAG grounded in policy, human-in-the-loop.

• On-premises model serving: Llama 3 70B on dedicated GPU infrastructure using vLLM for high-throughput inference. Model weights stored encrypted (AES-256) with offline update capability via signed model packages.
• Insurance-specific fine-tuning: Fine-tuned on 25,000 plus anonymised claim interactions, policy documents, and approved response templates. Training conducted on isolated infrastructure with synthetic data augmentation.
• RAG with policy grounding: Retrieval-augmented generation using indexed policy documents, terms and conditions, and approved response templates. Every response includes source citations for audit traceability.
• Human-in-the-loop governance: Confidence thresholds trigger automatic escalation. Complex claims, disputed amounts, and edge cases route to human handlers with AI-prepared context summaries.
• CRM integration: Bidirectional sync with existing CRM via secure internal APIs. Chatbot extracts structured data (policy numbers, claim types, customer details) and updates records with full change logging.

%%{init: {"theme":"base","themeVariables":{"background":"#0a0b0c","primaryColor":"#a9dbe6","primaryTextColor":"#efefe8","primaryBorderColor":"#a9dbe6","lineColor":"rgba(239,239,232,.3)","secondaryColor":"#0d0f11","tertiaryColor":"#0d0f11","textColor":"#efefe8","mainBkg":"#0d0f11","secondBkg":"#0a0b0c","border1":"rgba(239,239,232,.12)","border2":"rgba(239,239,232,.06)"}}}%%
flowchart LR
  Handler[Claims Handler]
  Portal[Chat Portal]
  Orchestrator[Orchestrator + HITL]
  vLLM[vLLM / Llama 3 70B]
  RAG[RAG Retriever]
  Vector[Vector Store
Policy Documents]
  CRM[Legacy CRM]
  Audit[Immutable Audit Log]
  Handler --> Portal
  Portal --> Orchestrator
  Orchestrator --> RAG
  RAG --> Vector
  Orchestrator --> vLLM
  vLLM --> Orchestrator
  Orchestrator --> CRM
  Orchestrator --> Audit
        

GDPR Article 28, 7-year retention, zero egress.

• Complete data sovereignty: Zero external API calls during operation. All inference, embedding generation, and retrieval happens within the client's network perimeter. No customer data ever leaves the premises.
• GDPR processor compliance: Documented data processing activities per Article 30. PII detection and handling policies. Data retention controls with automated purging. Subject access request (SAR) workflow integration.
• Encryption throughout: TLS 1.3 for all internal service communication. AES-256 encryption for data at rest including conversation logs and model weights. Database-level encryption with customer-managed keys.
• Audit trail: Every interaction logged with timestamp, user context, input hash, model version, retrieved documents, generated response, confidence score, and any human interventions. Logs retained for 7 years per insurance record-keeping requirements.
• Access control: LDAP integration with existing identity management. Role-based access (Claims Handler, Supervisor, Admin, Auditor). All access logged and reviewable.
• Prompt injection prevention: Input sanitisation, output filtering, and system prompt protection. Regular adversarial testing in CI.

Measured productivity, zero incidents.

• 80% reduction in repetitive claims handler workload, measured over 3-month baseline.
• Source citations on 100% of assistant responses, grounded in policy documents.
• Zero external API calls over 18 months of production operation.
• DPIA signed off by the client's Data Protection Officer before go-live.
• Faster onboarding: new handler ramp-up from 6 weeks to 2 weeks with AI-prepared context.