The growing number of insurance claims and the need to handle them without increasing the number of human adjusters and without exceeding the settlement deadline.
Automation of the “Claims Settlement” Process
Client NameKooperativa
Client CountryCzech Republic
- Client typeEnterprise
- IndustryFinancial Services, Markets & Insurance
- Application areasOperations & Process Automation
- AI technologiesAI Agents & Task Orchestration, Large Language Models (LLMs), Machine Learning, Multimodal AI, Natural Language Processing (NLP)
- Business impactsEmployee Enablement & Productivity, Operational Efficiency & Cost Savings
- Data typesDocuments / Semi-structured Data, Image Data, Structured Tabular Data, Textual Data
- Delivery modelsConsulting, Custom Development, Product / Licensed Software
- DeploymentsOn-premise
- Key capabilitiesDecision Support & Augmented Analytics, Recognition, Classification & Tracking
- Project stagesScaling / Expanded Implementation
- Solution formsAPI / Micro-service Interface, Automated Backend Process, Multimodal Interface, Plugin / Extension for an existing system
Solution Description
Problem description
Solution
A solution was created for automated claims settlement that can process documents submitted by the insured (medical reports, etc.). The system can receive reports in natural language, recognize the type of incident, and find the necessary information in Kooperativa’s internal systems. Based on medical reports, it can determine the diagnosis required for settlement, without the need for adjuster intervention in routine cases. Moreover, it can recognize which complex cases require the involvement of a human adjuster. This brings a high degree of automation, faster claims processing, and reduced error rates.
Main Users of the Solution
Claims adjusters.
Project timeframe (months)
24
Technologies used
Custom classification model, LLM
Additional services
- Audit / feasibility study
- Identification and prioritization of suitable use-cases
- Data collection and pre-processing
- AI model selection and customisation
- Compliance/regulatory support
- Providing MLOps infrastructure
Use of Personal / Regulated Data
Yes
Implementation
Project Owner on the Client's Side
Head of functional/operational unit
Participation on the Client's Side
- Business / Product Owner
- Domain / process experts
- Software & Data Engineering / IT Ops
- Project and change management
- Quality, safety, compliance
- End users
Form of Supplier Involvement
Full implementation
Operation and Maintenance
Operational Model
Joint management
Needed Competencies on the Client's Side
L1 and L2 support
Other Resources or Infrastructure
N/A
Impact and Results
Qualitative Benefits
Increased comfort for human adjusters, retention of know-how, and improved accuracy. Creation of a solid foundation for implementing AI in other areas.
Quantitative Results
Diagnostic accuracy 97.8% with 60% process automation. Claims settlement time reduced to 1–2 minutes.
Client Feedback
Highly positive statement by Ondřej Poul on LinkedIn: “First in the Czech Republic! We’re settling life accident claims at Kooperativa with an AI automaton. I’m not talking about a successful PoC, or just OCR data from medical documentation, or simple non-life claims. No, no, no! I mean a fully end-to-end process of life accident claims settlement”
Lessons Learned and Recommendations
Key Success Factors
Clearly defined business case, client–provider cooperation, high expertise of the provider.
Biggest Challenges
Balancing achieved accuracy with financial costs; Implementation of breakthrough AI technologies in a regulated industry.
Recommendation for Others
Have clearly defined and unambiguously measurable goals. Your business case must also include operational costs.
Promotion
- CompanyThe MAMA AI
- ContactJiří Vrobel
- Emailsales@themama.ai
- Websitehttps://themama.ai
- AddressRevoluční 764/17, 110 00 Praha