Standard AI Analytics
What is this? Standard AI Analytics helps regional managers spot stockouts, detect suspicious behavior, and track checkout anomalies across multiple stores.
Timeline2023 - 2024
*Some visuals and UI elements have been modified to comply with NDA requirements.
See the NACs report here:
https://www.convenience.org/Media/Daily/2023/November/22/4-Standard-AI-Technology-Curb-Inventory-Loss_Tech
Standard AI later pivoted away from autonomous checkout and fully embraced this direction: visual analysis powered by smart cameras and computer vision.
Overview
In high-theft, high-traffic areas like tobacco displays and beer caves, even a single blind spot can lead to thousands in losses. But most stores don’t have the budget—or the space—for a full-store AI system. That’s where the Standard AI Analytics Tool comes in. As a lightweight computer vision solution, it pairs a single camera with smart software to track stockouts, detect suspicious behavior, and give retail managers visibility where it matters most.
As the Lead Product Designer, I shaped the first version of this tool from the ground up—defining its structure, designing its interface, and demoing it to prospective customers. My work helped lay the foundation for what would become Standard AI’s new product direction.
The Problem
Loss prevention in retail is often reactive and fragmented. Regional managers overseeing multiple locations had little visibility into:
- Out-of-stock inventory in key revenue zones
- Potential theft at checkout or self-serve areas
- Repeat suspicious behavior patterns
And even when cameras were installed, most video went unwatched—lost in outdated systems and unsearchable footage.
“We only find out something went wrong when it’s already too late.”
— Convenience Retail Manager, Interview
The Design Opportunity
How might we help regional managers monitor high-risk store areas—without overwhelming them with footage or data?
We identified a sweet spot: small-to-midsize retailers with multiple locations and tight margins. These teams needed a solution that was:
- Cost-efficient
- Easy to install (just one camera per zone)
- Actionable—not just a flood of raw video
Our primary users were regional managers responsible for 10–50 stores, often juggling operations, staffing, and inventory issues daily.
Product Vision
The product would be structured around three core tools:
AI Chatbot
Ask questions like “Which stores had the most missed scans this week?” and get instant insights.
Event Library
An organized feed of automatically captured and labeled events—stockouts, suspicious checkouts, and more.
Analytics Dashboard
A cross-store dashboard showing trends in theft risk, inventory gaps, and compliance issues.
Smart Blink
Labeling a “take” action often begins with confirming whether a product was actually removed from the shelf. The Smart Blink feature simplifies this by showing a quick ping-pong animation of ±5 seconds around the playhead—highlighting any items that were taken, so reviewers can spot changes instantly and label with confidence.
Dynamic Camogram
By analyzing store planograms, our machine learning algorithm learns to make educated guesses about which products occupy specific shelf locations. We integrated this visual search capability directly into the UI—transforming the shelf itself into an interactive interface, where data labelers can perform precise, direct manipulation with speed and clarity.
A Simple Yet Powerful Combo
Combining the 2 main features, the data labeler gets a more streamlined journey when labeling an action. Reducing the average labeling time from 2min to less than 30 second.
Comment Menu
In real-world scenarios, interactions are often more complex than simply taking or placing a product on a shelf. We redesigned the comment menu to give data labelers an easy way to “bail out” of frustrating cases, while also enabling the system to capture, sort, and learn from a wide range of edge cases.
Keyboard Shortcut
After closely observing the interaction patterns of dozens of data labelers with QA experts, we developed an intuitive and easy-to-learn hotkey system—and tested it ourselves to ensure usability. The shortcuts were inspired by traditional video editing tools and, surprisingly, the classic control schemes of video games.
Impact
We soft-launched the new interaction in a simulated “Shadow Mode” and gradually rolled it out:- 📉 Review time dropped from ~2 mins to <1 minute
- 💸 Cost per store decreased by 83%
- 🤖 Accuracy of product detection rose to 96%
- 🚀 The feature shipped in production across 21+ stores
Dynamic Camogram turned a tedious task into a guided, intuitive interaction—training better AI while creating a better experience for the humans behind it.
Reflection
This project reinforced a core belief: great AI starts with great human tools. By turning data labeling into a collaborative loop between people and machine, we made Standard AI’s models not just smarter—but more scalable and sustainable.
"Designing for people behind the curtain is what makes the magic on stage possible."
© 2025 Ke Ding. All rights reserved.