Simpego uses Amazon Bedrock and Claude Opus to extract data from Swiss insurance claim documents
Simpego· SwitzerlandAmazon Bedrock · ClaudeSwiss digital insurer Simpego and AWS partner copebit built a serverless, event-driven extraction pipeline on Amazon Bedrock with Anthropic's Claude Opus to replace template-based OCR for multilingual Swiss invoices, with schema validation, arithmetic checks and human-in-the-loop review. The source reports 95% of cases without manual intervention and about 30 seconds per document.
Overview
Swiss digital insurer Simpego and AWS partner copebit built a serverless, event-driven extraction pipeline on Amazon Bedrock with Anthropic's Claude Opus to replace template-based OCR for multilingual Swiss invoices, with schema validation, arithmetic checks and human-in-the-loop review. The source reports 95% of cases without manual intervention and about 30 seconds per document.
This entry has 15 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
Claims specialists had to manually sift through line items and complex Swiss VAT details from thousands of documents per month. The process was slow, did not scale, and took time away from resolving claims.
The solution
Simpego and AWS partner copebit built a fully serverless, event-driven extraction pipeline on Amazon Bedrock using Anthropic's Claude Opus in place of template-based OCR. Output is checked by schema validation and arithmetic checks, and the claims specialist verifies the pre-filled data.
Reported business value
The source reports that 95% of cases need no manual intervention, with an average turnaround of roughly 30 seconds per document, and that the project went from kickoff to production in two months.
Sources
Open any source and check the claim yourself — that is the point of the register.
This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)
Other insurance entries in the register.
UNIQA SEE cuts health insurance claims processing times by 90% with Azure AI
UNIQA SEE's claims handlers faced fragmented documents, manual tasks, and heavy call-center reliance that slowed claims processing. Using Microsoft Azure AI alongside Microsoft Foundry, Azure Document Intelligence, and Azure OpenAI, UNIQA SEE built an end-to-end AI-driven medical referral solution that extracts, validates, and integrates referral letter data via APIs into the core claims system. The solution reduced claims processing time from 15-30 minutes to 2-3 minutes (an 85-90% reduction), lowered costs and call volumes, and freed staff for higher-value work. UNIQA SEE also introduced a self-service web and mobile app allowing customers to submit medical referral letters digitally. UNIQA SEE became the first insurer in Southeastern Europe to implement an AI-powered business process solution of this kind.
UNIQA Insurance Group· AustriaMicrosoft Azure AI · Microsoft Foundry · Azure Document Intelligence +1
How Mapfre Insurance modernized fraud claims with Amazon EMR Serverless
Mapfre Insurance, the number one auto and home insurer in Massachusetts, modernized fraud detection by combining graph-based features from Neo4j with machine learning models deployed on AWS, using Amazon EMR Serverless, Apache Iceberg tables on Amazon S3, AWS Glue Data Catalog, AWS Lake Formation, and Amazon MWAA for orchestration. Fraud predictions integrate directly with Guidewire Claims via AWS Lambda, automatically creating claim activities showing the top model drivers for adjusters. The initiative, covering Massachusetts Auto insurance and later expanded to Home insurance, has delivered more than $5 million in Net Present Value, with detection accuracy improved 50-135 percent compared to baseline methods.
Mapfre Insurance· United StatesAmazon EMR Serverless · Apache Iceberg · AWS Glue Data Catalog +5Efficiency meets data sovereignty: Lector automates document processing with AI
Lector, a platform for intelligent document processing used by more than 60 corporate customers including over 25 health insurers, migrated its productive cloud services from a major American cloud provider to OVHcloud's German data centre to meet GDPR and data-sovereignty requirements. Using OVHcloud Managed Kubernetes, S3-compatible Object Storage, and AI Training/AI Deploy/AI Endpoint services, Lector achieved over 80% time savings in document processing across more than 500 million pages processed to date, while reducing the operational burden of running Kafka and MongoDB themselves.
lector.ai GmbHKubernetes · S3-compatible Object Storage · Kafka +2AXA builds Secure GPT to give 140,000 employees safe generative AI access
AXA, a global insurance and asset management group with 93 million clients in 51+ countries, built AXA Secure GPT in under three months, a generative AI platform powered by Azure OpenAI Service that gives its 140,000 employees secure, GDPR-compliant access to generative AI for tasks like text generation, translation, and code generation, without data leaving AXA's dedicated cloud tenant. The platform uses Prompt Shields and AXA's own security layer on top of Microsoft's content filtering, and was rolled out first to AXA Group Operations across 14 countries with a curated library of 100+ department-specific prompts.
AXA· FranceAzure OpenAI Service · Azure AI StudioWas this helpful?
Your feedback helps us improve our use case database