AI Feedback & Insights Agent

Agentic Workflow DesignAI DesignUX Research

AI Feedback & Insights Agent

Willis Towers Watson · Individual Marketplace · 2025–2026

During Medicare Open Enrollment, researchers were spending entire days manually categorizing participant feedback. I realized the bottleneck wasn't the volume — it was the workflow. So I built a system that automated the process, closed the expert gap, and reduced synthesis from hours to minutes.

Participant Listening Agent overview showing agent description, analytics with 128 sessions, 76% engagement, 4.3/5 satisfaction, and the live test panel

95%

Categorization accuracy

8+ hrs → min

Synthesis time

5 days → same day

Insight delivery

4.5 / 5

Stakeholder satisfaction

My Role

Senior UX Designer (self-initiated)

Stack

Copilot Studio, Qualtrics API, Dataverse, Power Automate

Timeline

2025–2026

Type

Agentic AI workflow, internal tooling

Interested?

Want to talk through the methodology or the build?

Next Case Study

People-First Enrollment Redesign

Read case study →