Challenge
PepsiCo's legacy New Item Tracker, Quaker Forecast Tracker, and Gatorade Forecast Tracker apps lacked branding, consistency, usability, and connectivity — built by a product manager without any design background.
Process
As principal UX UI Designer on a team of 8, I worked closely with the product owner to understand content, usage, and user roles. I researched and designed a new usable UI for all three brands, maximizing PowerApps for functionality and consistency while incorporating individual branding for each PepsiCo brand.
Impact
In the key user group of account managers, product and store managers, the user satisfaction rate reached 100%. VPN was no longer needed. Forecasting was simplified, the UI became more intuitive, and account and store managers gained easier, more accurate forecasting for immediate and longer-term product needs.
Challenge
PepsiCo now forecasts roughly 125 million weekly combinations across a network of direct-store-delivery, warehouse distribution, and e-commerce fulfillment, blending AI-driven demand models with direct retailer data-sharing at a scale the 2020 trackers were never built for. The open question: what would it look like if that intelligence reached the account executives and store managers actually working the shelf, instead of stopping at the forecasting team?
Process
For my AI-for-UX-design coursework, I designed a concept successor to the three legacy trackers: one role-based dashboard — Product Manager, Account Executive, Store Manager, Admin — that surfaces AI-generated recommendations (regional demand shifts, predicted stockouts, auto-drafted variance reasons) alongside the reasoning behind each one and a required human approval step before anything posts. That last part reflects the throughline in my recent work: designing accountability and human oversight into AI-assisted, failure-intolerant systems. Each PepsiCo brand keeps its own logo and color identity, unified under one shared shell rather than three disconnected apps.
Vision
This is a concept exploration, not a shipped feature — a look at how the legacy trackers could evolve now that PepsiCo's own forecasting stack has moved toward predictive, explainable AI. The interactive prototype below lets you switch roles and brands to see how the same recommendation engine would surface differently depending on who's looking at it.
View interactive concept