Fill every truck. Plan every mile with AI. Scale it across eight thousand lanes.
(Your Canadian retailer pilot on slashing empty return miles is awesome. This is how you replicate it across the network.)
How do you close 46 points of emissions intensity across 8,000 lanes, without hiring a 1,000-person planning org?
By better asset utilization. We can help. Here's how.
Caddie takes the plan you already have, turns it into minute by minute dispatch decisions, and writes the outcome back to your system of record. A shipment enters at Pairing, exits at Settlement, autonomously, in minutes. Then the next shipment enters. The loop runs 24/7.
Every number ties to a primary public source. ATRI for deadhead and per-mile cost. EPA SmartWay for diesel emissions. AAR for rail vs road. P&G's own disclosed pilot for the anchor. Pull the sliders. See what one lever (collaborative freight) delivers on its own. Then compound with planning, warehousing, and modal shift on the same platform.
Full methodology, formulas, assumptions, and an Excel-ready model are maintained separately. Every assumption is vettable.
Open the calculator in a new tab for a full-width view.
Pair economics are a density problem. Iowa City has the density. No other P&G plant does.
Megan Katic, Director of Beauty Care Supply Chain, has publicly listed space optimization, automation, and AI as her priority challenges. The Dock and Yard Agent is the direct answer.
One AI-native platform. Demand sensing, inventory, dispatch, execution, freight settlement, sustainability reporting. All on one intelligence layer that sits above the systems you already own.







We leave the room with three scoped experiments and a shared view of what the Supply Chain 3.0 execution layer looks like next quarter. Three questions we'd most want to ask you before the session. Your answers tell us what experiments to bring to the table.
Why we believe this works at scale. Uber Freight reported at Deliver 2025: -38% scheduling time, -15% overdue loads, ~-80% delay duration with agentic AI [5]. That architecture works at the broker layer. Moving it to the shipper unlocks the collaborative-miles opportunity.