Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.
Title
Simpego uses Amazon Bedrock and Claude Opus to extract data from Swiss insurance claim documents
…some process steps and ultimately satisfy customer expectations. To solve this, Simpego and AWS Advanced Partner copebit built a fully serverless, generative AI-first extraction pipeline using Amazon Bedrock . By using Anthropic’s Claude Opus model, they transitioned from traditional op…
Description
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.
…ully serverless, generative AI-first extraction pipeline using Amazon Bedrock . By using Anthropic’s Claude Opus model, they transitioned from traditional optical character recognition (OCR) with rigid templates to a flexible, intelligent extraction strategy. A large language model (LLM) can reason about the content of a document it has…
Company
Simpego
…ing: a fast resolution. Every extra day between filing and payout erodes trust. For Simpego, a digital-first Swiss insurer, that urgency shaped a clear engineering goal: to remove every unnecessary dela…
Country
Switzerland
…ing: a fast resolution. Every extra day between filing and payout erodes trust. For Simpego, a digital-first Swiss insurer, that urgency shaped a clear engineering goal: to remove every unnecessary dela…
Region
Europe
…ing: a fast resolution. Every extra day between filing and payout erodes trust. For Simpego, a digital-first Swiss insurer, that urgency shaped a clear engineering goal: to remove every unnecessary dela…
Industry
Insurance
…ing: a fast resolution. Every extra day between filing and payout erodes trust. For Simpego, a digital-first Swiss insurer, that urgency shaped a clear engineering goal: to remove every unnecessary dela…
Problem
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.
…tified the primary bottleneck that was causing these delays: manual data entry. 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 away precious time from claims specialists who needed to focus on efficiently and correctly resolving claims. Simpego need…
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.
…Technical Deep Dive Rather than adopting traditional OCR with rigid templates, Simpego and copebit built a fully serverless, event-driven pipeline on AWS. The pipeline follows an asynchronous, event-driven design that separates docume…
…line items and VAT amounts correctly sum up to the total amount on the invoice. Human-in-the-Loop: The claims specialist performs a final verification of the pre-filled data, correcting any minor extraction errors and serving as a continuous quality and…
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.
…rless scaling Today, the pipeline processes thousands of extractions per month, with an average turnaround of roughly 30 seconds per document. From upload to fully structured, pre-filled data ready for specialist review.…
…move to an LLM-based pipeline has transformed Simpego’s operational efficiency. The project moved from kickoff to production in just two months. Metric Before GenAI After GenAI Processing Speed Hours of manual entry Seconds…
…ssing Speed Hours of manual entry Seconds Efficiency Fully manual transcription 95% of cases without manual intervention Accuracy Prone to human errors High consistency Scalability Required more staff…
AI capabilities
Document Intelligence, Generative AI
…capable of contextual document understanding had arrived. Together, these made intelligent document processing the highest-impact automation opportunity in Simpego’s claims workflow. To bring the vision to production, Simpego partne…
Technology
Amazon Bedrock, Claude
…ully serverless, generative AI-first extraction pipeline using Amazon Bedrock . By using Anthropic’s Claude Opus model, they transitioned from traditional optical character recognition (OCR) with ri…
Deployment model
Cloud
…Rather than adopting traditional OCR with rigid templates, Simpego and copebit built a fully serverless, event-driven pipeline on AWS. The pipeline follows an asynchronous, event-driven design that separates docum…
Deployment options
cloud
…Rather than adopting traditional OCR with rigid templates, Simpego and copebit built a fully serverless, event-driven pipeline on AWS. The pipeline follows an asynchronous, event-driven design that separates docum…
Headline outcome
…ssing Speed Hours of manual entry Seconds Efficiency Fully manual transcription 95% of cases without manual intervention Accuracy Prone to human errors High consistency Scalability Required more staff…
Use case type
Document processing
…capable of contextual document understanding had arrived. Together, these made intelligent document processing the highest-impact automation opportunity in Simpego’s claims workflow. To bring the vision to production, Simpego partne…
