Agentic AI Insurance Claims
Designing the trust layer for AI-driven decisions
Where Trust Breaks (The Problem)
Insurance claims are slow and fragmented. AI improves speed but it also creates a trust gap. Decisions are made instantly but users are left without context, reasoning or control.
Drivers don’t understand decisions
Adjusters don’t trust AI outputs
→ Decisions happen faster than humans can verify them
What Needed to Change (The Goal)
The goal wasn’t automation, it was making AI decisions understandable, accountable, and usable by humans.
Design a claims experience that:
makes AI decisions transparent
keeps adjusters in control
reduces uncertainty for drivers
What Changed
(The Impact)
System Design Moves (What I did)
Exposed the “black box” failure in AI decision-making
Separated driver and adjuster workflows to reflect real-world roles
Turned AI outputs into explainable, editable decisions
Reframed prioritization around regulatory deadlines, not model confidence
Established trust as a measurable system metric
Reduced adjuster cognitive load by replacing fragmented tools with a unified system
Increased trust in AI decisions by exposing reasoning and confidence
Improved decision clarity by turning AI outputs into explainable, editable inputs
Created a human ↔ AI feedback loop through override and audit mechanisms.
