The claims platform behind 90% of the German market

Beyond the numbers, the system enabled quicker and more confident decision-making during claims assessments, reducing cognitive load for experts by surfacing the right information at the right moment, rather than requiring them to hunt through unstructured documents.

The integration of LLMs and Intelligent Document Processing (IDP) presented a rare opportunity, not just to improve the existing product, but to redesign and migrate the entire system from scratch into a new use case-based automation pipeline.

This required designing end-to-end user flows grounded in deep domain knowledge: understanding how insurance claims were originally processed by legal experts, medical professionals, and claims assessors, then unifying these into a single coherent, scalable system.

Manual claims processing was time-intensive by nature. Tasks that took hours were bottlenecked by repetitive document review, data extraction, and structured report writing. The emergence of LLM and IDP technology created a direct opportunity to automate the most labour-intensive parts of this workflow.

Understanding where automation opportunities existed required granular knowledge of how different expert types (legal, medical, administrative) approached claims at each stage. This domain research informed every design decision.

Working directly with over 90 insurance customers, I mapped the workflows, edge cases, and expert mental models the new system had to absorb. Claim types, user roles, and legal contexts vary too much for one-size-fits-all, so the flexibility had to live in the components and the flows.

Research focused on where manual work could be cut without eroding the expert's sense of control, the deciding factor for AI adoption in high-stakes work like medical injury claims.

User interviews were combined with business flow diagrams to bridge the gap between real user behaviour and underlying business logic. This dual lens (qualitative research alongside process mapping) allowed me to build an initial proof-of-concept grounded in both user needs and operational constraints.

I championed the project internally, presenting the proof-of-concept to stakeholders and driving approval to proceed, translating complex UX rationale into business value to secure buy-in across the organisation.

The core design challenge was making AI recommendations legible and actionable, not just technically functional. Insurance claims involve legal liability and medical judgment, so the system needed to present AI outputs with appropriate confidence framing, traceability, and override capability.

I led the design and development of the AI recommendation layer, working through questions of AI governance: when should the system act autonomously, when should it recommend, and when should it stay silent?

Every recommendation stayed attached to its evidence. An assessment could be opened back to the documents behind it: which document, which agent read it, and what that agent took the passage to imply. The assessor sees the chain rather than only the conclusion, so checking the system's work costs a click instead of a re-read of the file.

As Lead Product Designer, I had to balance trade-offs across user experience, business goals, technical constraints, and delivery timelines, especially for the MVP scope.

This meant prioritizing core user flows, clarity, and speed-to-market over edge cases, advanced customization, or long-term scalability in the first release. I also worked closely with stakeholders to align product vision with engineering feasibility and business priorities while managing scope and maintaining momentum.

NDA prevents naming the specifics. Here's how I categorize the judgment calls behind this work:

Next time, I'd cut irrelevant functionalities sooner and focus solely on championing those that would clearly make an impact. Simplification of old systems can spark opportunity. UX heuristics apply, and good ones can win over old habits of working.