European multi-line insurer co-develops generative AI solutions with Capgemini, including a travel insurance RAG chatbot with 91% accuracy
A European multi-line insurer worked with Capgemini across several business entities on a generative AI roadmap and solutions: multilingual meeting transcription and summarization (12x reduction in manual effort in that area), a RAG chatbot for ESG report analysis (with a comparative study of Mistral AI and GPT-4), and a RAG-based travel insurance chatbot that reached 91% accuracy in customer query responses with live agent validation.
Overview
A European multi-line insurer worked with Capgemini across several business entities on a generative AI roadmap and solutions: multilingual meeting transcription and summarization (12x reduction in manual effort in that area), a RAG chatbot for ESG report analysis (with a comparative study of Mistral AI and GPT-4), and a RAG-based travel insurance chatbot that reached 91% accuracy in customer query responses with live agent validation.
This entry has 13 published fields tied to exact passages in an immutable source capture.
Inspect the highlighted sourceThe challenge
The insurer sought to increase operational efficiency and enhance the employee and customer experience by adopting generative and agentic AI at scale, and first needed a clear direction and roadmap for choosing the most effective use cases.
The solution
Capgemini partnered with multiple business entities to create a strategic roadmap and co-develop generative AI solutions, starting with a comprehensive assessment of existing processes and systems. Solutions included multilingual meeting transcription and summarization, a RAG-architecture chatbot to analyze and generate ESG reports (with a comparative study of Mistral AI and GPT-4 models), and a RAG-based travel insurance chatbot built on the company's travel terms and conditions documents, delivered with business adoption playbooks.
Reported business value
Capgemini reports that one implementation achieved a 12-time reduction in the manual work of generating meeting summaries and accelerated that entity's time to market, and that the travel insurance chatbot achieved 91% accuracy with live agent validations. The source describes these as results in certain areas and states the insurer is now positioned to pursue a more efficient and AI-ready future.
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 +5Generali Luxembourg deploys a disconnected, sovereign AI environment with DEEP for AML/KYC document analysis
Generali Luxembourg, a life insurer, deployed open-source large language models on a dedicated environment hosted by DEEP (POST Group) in Luxembourg data centres, with no connection to the outside world, to meet supervisor data-confidentiality constraints. The first use case, still in the POC phase, supports AML/KYC operations by analysing customer-provided documents and cross-checking information; a human operator keeps the final decision. The source says the first use case took three months to deploy and that the time to respond to a new request, previously up to two days, will now be thirty minutes.
Generali Luxembourg· LuxembourgEfficiency 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 +2Was this helpful?
Your feedback helps us improve our use case database