End to end supply chain design.
Network optimization.
AI products that ship.
I help teams ship AI products that survive contact with real supply chain operations. 15+ years in the field. 5 continents. 11 production products shipped.
You're probably in this room.
Three areas I have the most confidence in.
Not the full supply chain alphabet soup. These three are where I've actually shipped production systems and have real case studies to back it up.
End to end supply chain design
Strategic design across the full flow. Sourcing, inventory, warehousing, distribution, last mile. Fifteen years of operational reality behind every recommendation.
- Sourcing & procurement
- Inventory & warehouse
- Distribution & last mile
Network optimization
Routing, node design, and disruption modeling. Decision systems for when the network has to absorb shock without losing service.
- Routing under uncertainty
- Disruption early warning
- Network redesign
AI product development
From customer interviews to shipped feature. I design AI products, partner with engineering on delivery, and make sure the math survives contact with operations.
- Discovery & user research
- Roadmap & specs
- Engineering partnership
Real systems with measured outcomes.
Case studies are how you can tell the work is real. Each one shows the problem, the approach, and the business impact. I desensitize the numbers when clients ask. I never make them up.
K-Means Customer Segmentation on US Retail Data
Most retail marketing budgets are flat per customer. But customer value isn't flat — it's a power law. Without segmentation, you overpay the cheap customers and underspend on the ones who actually carry the P&L.
Cutting Last-Mile Mileage by 59% with Vehicle Routing
Last-mile is the single most expensive line in a delivery P&L. Naive dispatch order — visit stops as parcels arrive — quietly burns 50–70% more kilometres than the optimised version. The math has existed since the 1950s; most ops teams still don't run it.
The Algorithm That Beats Intuition on the Floor
Most grocers lay out shelves by supplier or alphabetically — not by what shoppers actually buy together. The lift the floor leaves on the table is invisible until someone runs the data.
Supply Network Optimization with Linear Programming
Most supply-chain networks are sized by gut feel and Excel. The result is networks that are always 'a little too big in the wrong place'. Linear programming says exactly where the flow should go — and what it actually costs to respect every capacity constraint.
Don't just read about it. Run it.
The Bullwhip Effect is the single most common reason supply chains over-react. Try a few rounds below and watch small demand changes turn into chaos upstream. Now imagine this running on your real data.
The Bullwhip Effect
A small change in customer demand causes massive swings upstream in a supply chain. This simulator lets you see why — and what fixes it.
Simulation Rules
Each tier can only see orders from the tier directly below it — not actual customer demand. Orders take 2 weeks to arrive. The retailer's ordering strategy is what you control — everything upstream reacts automatically.
Insights on AI in logistics
Stories and analysis from the AI × Supply Chain world.
The Supply Chain Consultant's AI Reckoning: What Gets Replaced, What Gets Elevated, and How to Position Yourself
I Tested Claude, GPT, and 5 Other LLMs on Real Supply Chain Problems. No Single Model Won.
Why Solo AI Agents Are Dead. The 1,445% Surge in Multi-Agent Systems, Explained.
The Delegate-Review-Own Playbook. Why the Companies Winning with AI Aren't Replacing Humans.
Claude Code Hit $1 Billion in 6 Months. Then $2.5 Billion in 3 More.
The Enterprise Agentic AI Market Just Hit $7.51 Billion.
OpenClaw Just Became the Fastest-Growing Repo in GitHub History.
The Supply Chain Consultant's AI Reckoning: What Gets Replaced, What Gets Elevated, and How to Position Yourself
I Tested Claude, GPT, and 5 Other LLMs on Real Supply Chain Problems. No Single Model Won.
Why Solo AI Agents Are Dead. The 1,445% Surge in Multi-Agent Systems, Explained.
The Delegate-Review-Own Playbook. Why the Companies Winning with AI Aren't Replacing Humans.
Claude Code Hit $1 Billion in 6 Months. Then $2.5 Billion in 3 More.
The Enterprise Agentic AI Market Just Hit $7.51 Billion.
OpenClaw Just Became the Fastest-Growing Repo in GitHub History.
Practitioner first. Theorist second.
Doctorate in Operations Research and Supply Chain from Rutgers. MBA from Carnegie Mellon Tepper. Six Sigma Black Belt. CLTD instructor. The credential that matters more is this. I started with pallets and 3 AM calls about stuck containers. I'm the person you want wiring intelligence into operations that have to ship whether or not the AI works.
Ready to move beyond pilots?
Whether you're scoping your first AI project or scaling one that's already running, let's talk. I reply within one business day.
Book a 30-min scoping call