AI Feedback Intelligence Tool

Simplifying Complex Customer Feedback with Gen AI

Dashboard Image
Dashboard Image
Dashboard Image

ROLE

ROLE

Lead UX Designer

Lead UX Designer

SKILLS

SKILLS

UX Strategy

UX Research

Data Visualization

UX Strategy

UX Research

Data Visualization

STAKEHOLDERS

STAKEHOLDERS

Product Managers

Journey Owners

Customer Support

Product Managers

Journey Owners

Customer Support

OVERVIEW ✍️

As a UX designer focused on scalable enterprise solutions, I led the design of an internal AI-powered tool that automated how Vanguard teams analyze customer feedback.

Previously, teams had to manually review over 1,000 feedback entries per week—an inefficient and error-prone process.

FINAL PRODUCTS 🖥️

Spot Patterns You Can’t See

Spot Patterns You Can’t See

The AI scans thousands of entries and uncovers recurring themes, sentiment shifts, and hidden pain points—surfacing insights teams may have otherwise missed.

Doctor working
Doctor working
Doctor working
Doctor working
Doctor working
Doctor working

FINAL PRODUCTS 🖥️

Turn Hours of Work into Seconds

Turn Hours of Work into Seconds

What once took entire research teams days to process is now completed in seconds. The AI automatically organizes and summarizes feedback, allowing teams to spend less time sorting data and more time acting on it.

THE PROBLEM 🚩

Vanguard saw a sharp rise in customer feedback as rollover transactions surged—jumping from 13,000+ in 2022 to 30,000+ in 2024. Alongside this, monthly feedback entries grew from just 200+ to over 1,000.

The existing process required teams to manually sift through every comment, which:

  • Consumed hours of effort each week

  • Left most feedback unread or undocumented

  • Delayed discovery of urgent issues like broken features

  • Limited the company’s ability to act quickly on user needs

In short, the more transactions we processed, the more unmanageable the feedback became—overwhelming teams and stalling meaningful action.

AI DESIGN ♾️ DESIGN AI

Designing for AI goes far beyond creating an interface—it’s about shaping how people trust machine insights. To achieve this, I:

  • Partnered with engineers to align design with data pipelines and model behavior

  • Ensured outputs were both explainable and reliable

  • Created clear visualizations that turned raw data into actionable decisions

My approach emphasized clarity, transparency, and trust—helping users not only see what the AI uncovered, but also understand how to use those insights with confidence. This reinforced my belief that great AI design is about simplifying complexity into decisions people can act on.

KEY FEATURES 🖥️

The dashboard was designed to cut through the noise of thousands of comments and give teams clarity at a glance. High-level metrics show total entries, overall sentiment, and daily trends, while maps and charts reveal where issues are happening and how they shift over time.

When deeper investigation is needed, teams can use detailed tables to:

  • Filter results by sector, device, or journey step

  • Trace issues back to their specific source

  • Compare patterns across different customer segments

  • Validate insights before sharing with other teams

DESIGN ITERATIONS ✏️

Early iterations of the dashboard experimented with different ways of structuring information. At first, we prioritized content strictly by importance, but this forced users to scan back and forth across the page and created unnecessary cognitive load.

Through testing, we shifted to a Z-shaped reading pattern, which aligns with natural eye movement from top-left to bottom-right. This adjustment improved accessibility, reduced effort, and made it easier for teams to quickly grasp key insights without missing critical details.

THE SOLUTION 🎲

To address the overwhelming volume of feedback, I led the design of an AI-powered tool that automates the end-to-end analysis process. Working cross-functionally with engineers and strategists, I mapped out the data pipeline, prioritized user pain points, and created a streamlined interface that enables teams to extract insights in real time.

The tool was built to adapt to different team workflows, helping them surface trends, monitor sentiment, and act quickly on what matters most.

FINAL PRODUCTS 🖥️

The final product of the tool inspired my passion in solving complex real-world problems with the combination of Data and AI. Data is the future, and by automating this manual process, I learn to deliver products that not only improved operational efficiency, but also help business understand their product metrics, users' needs and expectations.

✅ Improving efficiency and streamlining the feedback analysis process

✅ Empowering stakeholders with timely and actionable insights

✅ Enabling Vanguard to make informed decisions that aligned with user needs

  • 01

    Cut 99.9% of Review Time

    Turned 96+ hours of manual feedback review into minutes. Reduced analysis cost from $40,000 to just 50 cents per week with Gen AI.

  • Scaled to 10+ Teams

    After 3 Town Hall presentations, the tool was adopted across 10+ internal teams, driving alignment and reducing duplicated efforts.

    02

  • Surfaced Critical Issues Instantly

    AI-powered alerts flagged broken features in real time—no more waiting for weekly meetings to catch urgent problems.

    03

  • Empowered Better Decisions

    Smart filters, sentiment tracking, and visual summaries helped teams focus on what matters most—and act on it fast.

    04

  • 01

    Cut 99.9% of Review Time

    Turned 96+ hours of manual feedback review into minutes. Reduced analysis cost from $40,000 to just 50 cents per week with Gen AI.

  • Scaled to 10+ Teams

    After 3 Town Hall presentations, the tool was adopted across 10+ internal teams, driving alignment and reducing duplicated efforts.

    02

  • Surfaced Critical Issues Instantly

    AI-powered alerts flagged broken features in real time—no more waiting for weekly meetings to catch urgent problems.

    03

  • Empowered Better Decisions

    Smart filters, sentiment tracking, and visual summaries helped teams focus on what matters most—and act on it fast.

    04

  • 01

    Cut 99.9% of Review Time

    Turned 96+ hours of manual feedback review into minutes. Reduced analysis cost from $40,000 to just 50 cents per week with Gen AI.

  • Scaled to 10+ Teams

    After 3 Town Hall presentations, the tool was adopted across 10+ internal teams, driving alignment and reducing duplicated efforts.

    02

  • Surfaced Critical Issues Instantly

    AI-powered alerts flagged broken features in real time—no more waiting for weekly meetings to catch urgent problems.

    03

  • Empowered Better Decisions

    Smart filters, sentiment tracking, and visual summaries helped teams focus on what matters most—and act on it fast.

    04