Amazon Case Study

AI Health Benefits Assistant

AI Health Benefits Assistant interface screens

Overview

I designed a GenAI-powered chatbot for Amazon's Benefits Management Console, from zero to shipped product. Worked with engineering, data science, and product to build a conversational assistant that helps admins resolve complex benefit queries faster and with more confidence.

Goals:

  1. Reduce time-to-resolution for complex benefit queries.
  2. Build trust in AI-generated responses through transparency and source attribution.
  3. Create a scalable conversational pattern for future AI integrations across Amazon benefits.
Lead Product Designer
End-to-End UX Design, Research Synthesis, AI Trust Framework
PM, 3 Engineers, Data Scientist, UX Researcher
6 months (2025)

The Challenge

Benefits admins handle thousands of queries daily across coverage, eligibility, and plan details. They're stuck navigating fragmented docs, 4+ disconnected systems, and edge cases that need deep domain expertise.

Reduce operational cost of benefit query resolution while maintaining accuracy.

Get reliable answers without switching between 4+ systems and outdated documentation.

The Benefits Management Console before AI integration

The Benefits Management Console before AI integration

Problem to solve

Administrators lack a unified, trustworthy source of answers, leading to slow resolutions, inconsistent responses, and declining satisfaction scores.

4+ systems

Admins had to switch between disconnected tools to resolve a single employee query

Research

I ran contextual inquiry with 12 benefits admins, mapped their existing workflows, analysed 3 months of query data, and benchmarked AI assistants for trust patterns. Key findings:

How might we

How might we design an AI assistant that administrators trust enough to integrate into their daily workflow while maintaining accuracy and accountability?

12 admins

Participated in contextual inquiry, revealing trust as the primary barrier to AI adoption

Design Strategy

Weekly iteration cycles with stakeholder reviews. I explored three interaction models (sidebar panel, full-page, and embedded) and tested each with 8 admins in moderated sessions. Three questions guided every decision:

  1. "Can I trust this answer enough to act on it?"
  2. "Where did this information come from?"
  3. "What do I do when the AI doesn't know?"
AI Assistant integrated into the benefits portal with intro state and suggested actions

AI Assistant integrated into the benefits portal with intro prompts and suggested actions

Solution

A graduated confidence system, built into the existing benefits portal workflow:

AI Trust Framework

AI response with interactive suggestion links and source attribution

Response with interactive links, reasoning indicator, and source attribution

Conversation flow with feedback controls and expandable sources

Conversation flow with feedback controls and expandable sources

Impact

30%
Reduction in cognitive load
~$4.75M
OpEx savings per year
500K→350K
Annual call volume reduction
1 system
Replaced 4+ disconnected tools

What I learned

Trust is earned in small, consistent steps

The confidence indicator drove the most positive feedback. Users needed to know when the AI was unsure, not for it to be perfect.

Ship the smallest valuable thing first

Starting with FAQ-only scope let us validate trust patterns before expanding to complex multi-step queries and edge cases.

Design for the skeptic, not the believer

The admins who trusted AI least became our strongest advocates once they could verify every source and override any suggestion.

Next Case Study

A verification system saving $27-51M per year →