In this episode of The New Warehouse Podcast, Kevin chats with Bart Gadeyne, founder and CEO of Optioryx, about how his company helps warehouses digitize and optimize warehouse operations. Drawing on over a decade of experience in logistics optimization, Bart shares how Optioryx began with solving “too much air in shipments” and grew into a suite of AI-powered tools for 3D load building, slotting, picking optimization, and mobile SKU dimensioning.
The conversation explores why accurate master data is critical before implementing automation, how to evaluate AI’s role in your operation, and how digital twins can provide actionable insights without costly IoT integrations. Bart also offers a practical roadmap for warehouse leaders to identify high-impact optimization opportunities before making investments in robotics or full automation.
Building Smarter Warehouse Foundations
Optioryx’s journey started with tackling inefficiencies in packaging. “We saw that too much air was being shipped in boxes, stacked on pallets, and also in trucks… so we built a 3D Tetris optimization algorithm to really stack goods as efficiently as possible.” From there, the company expanded into picking and slotting optimization, reducing walk distances by 20–55%.
Their digital twin platform allows operators to upload data, run simulations, and see immediate productivity impact. Instead of chasing automation trends prematurely, Bart advises starting with process control and accurate data: “Everything should start with the process you have and see what you could improve. If that involves applying AI, fantastic. If it doesn’t, that’s fine too.”
Why Master Data is the Cornerstone of Optimizing Warehouse Operations
One recurring challenge for optimizing warehouse operations, Bart sees, is poor master data, especially SKU and pallet dimensions. “If you don’t have the right master data, you’ll have so many follow-up issues during other warehouse processes.” Optioryx’s mobile app solves this with camera-based dimensioning, barcode scanning, and AI-driven data capture.
Use cases span from accurate transport cost estimation to ensuring pallets fit rack locations and reducing rehandling during picking. Without this foundation, even the most advanced automation systems will underperform. “Most solutions—robotics, AI, anything like that—won’t deliver the success you expect if the data isn’t right from the start.”
Making Digital Twins Accessible
While “digital twin” often conjures visions of expensive IoT-driven systems, Optioryx takes a more approachable path. Their model integrates warehouse layouts, algorithms, and customer data via WMS connections, eliminating the need for costly sensors. “We try to be that solution where you can just drop in data, see where the optimization potential is, and if you’re convinced, link it to your WMS and you’re good to go.”
By making simulations easy to run, warehouse engineers can test layout changes, equipment purchases, and process tweaks before committing resources. This makes the tool viable for mid- to large-scale B2C operations, particularly those with manual trolley picking and multiple pickers.
Key Takeaways on Optimizing Warehouse Operations
- Start optimization with process evaluation and accurate master data before pursuing large-scale automation.
- Mobile dimensioning technology reduces manual measuring and improves data accuracy across multiple warehouse processes.
- Picking optimization can cut walk distances by 20–55%, delivering rapid ROI without significant capital investments.
- Digital twins don’t have to be IoT-heavy—low-threshold data-driven models can provide powerful simulations and insights.
- Combining AI with metaheuristics yields faster, high-quality solutions for complex problems like slotting optimization.
