Document Processing
Claim handlers were managing dozens of cases each day while manually navigating documents, guidelines, and deadlines, which slowed claims processing and left less time for higher-value decision-making.
Reported impact
The proof of concept showed measurable gains in productivity and process automation, and the solution is now moving into production to improve efficiency, accuracy, and decision-making in claims handling while creating a reusable AI blueprint for wider Generali deployment.
Generali Switzerland, working with Group Data, AI & Automation (DAIA) and the House of Insurtech Switzerland (HITS), built KAssis as an internally developed GenAI knowledge assistant for insurance claims handling. The implementation is designed around the material claim handlers already use in daily work: claims documents, internal guidelines, and deadline-related information. KAssis uses that content to help staff find information quickly, extract key data from case material, flag inconsistencies, and suggest possible settlement options during claim review. The assistant is being hardened from a proof of concept into a production-ready deployment for Switzerland, with collaboration from frontline claim handlers and compliance with Generali data-security standards. The source does not name external models, storage services, or APIs, but it does position KAssis as a reusable, scalable in-house AI capability intended first for Non-Life teams in Switzerland and later for broader Group reuse.
Claims documents, guidelines, and deadline-related case information are used by KAssis to support claim handlers. The assistant surfaces relevant information, extracts key data, identifies inconsistencies, and proposes settlement options, after which handlers use those outputs to make faster and more informed claim decisions.
"At the beginning of the year, the project team conducted a Proof of Concept (PoC) analyzing 50 claims of varying complexity."
"Claim handlers manage dozens of cases daily, navigating a maze of documents, guidelines, and deadlines. Much of this work remains manual"
"KAssis aims to change that by acting as an intelligent assistant, helping handlers find information quickly extract key data flag inconsistencies and proactively suggest possible settlement options"
"KAssis, an in-house GenAI-powered knowledge assistant designed to transform the way claim handlers work."
"The results were promising, demonstrating measurable gains in productivity and process automation."
"developed internally, in close collaboration with the claim handlers and ensuring compliance with Generali’s standards for data security."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
In-house Sample May 12, 2026 Deutsche Bank Deutsche Bank needed to review third-party vendors' documentary evidence against its control framework and regulatory expectations faster without removing expert judgement, because onboarding and periodic reviews… A manual review would typically take around 30 minutes per evidence document. TPRM AI In-house Sample Oct 20, 2025 BNY BNY wanted to scale AI adoption across the company without fragmented point solutions, while maintaining strong governance, risk management, compliance controls, and practical support for workflows such as payments,… 75% more AI solutions in production compared to the prior quarter Contract Review Assistant · Eliza · Eliza agents In-house Sample Sep 17, 2025 Citi Citi needed to help employees work through large volumes of internal documents, drafting tasks, and policy questions more efficiently while supporting faster decision-making, compliance, and risk control. approximately 166,000 Citi colleagues across 76 countries will have access to Citi’s Gen AI tools Citi Assist · Citi Stylus · Citi Stylus Workspaces 