KAssis: Generali’s In-House GenAI Knowledge Assistant Moves from Concept to Reality

Addressing a Critical Challenge

Claim handlers manage dozens of cases daily, navigating a maze of documents, guidelines, and deadlines. Much of this work remains manual, slowing down processes and leaving little time for value-added activities. 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, thus supporting faster and more informed decision-making.

From Proof of Concept to Production

At the beginning of the year, the project team conducted a Proof of Concept (PoC) analyzing 50 claims of varying complexity. The results were promising, demonstrating measurable gains in productivity and process automation. Building on this success, the next phase will see KAssis evolve into a production-ready solution for deployment in Switzerland.

Built for Generali, by Generali

Unlike off-the-shelf solutions, KAssis is being developed internally, in close collaboration with the claim handlers and ensuring compliance with Generali’s standards for data security. This approach enabling scalability across other business units and lines of business once validated in Switzerland.

The immediate focus is on testing and expanding further functionalities, hardening the solution for production, and rolling it out to Non-Life teams in Switzerland. Once proven, KAssis is expected to serve as a blueprint for similar deployments across the Generali Group.

KAssis is more than a tool—it’s a signal of Generali’s evolution: building in-house AI capabilities that deliver real business impact while keeping people at the centre.