Fewer miles for every delivery
We plan the shortest working day for every van, and re-plan it when orders change.
Our plan for a distributor running 15 vans
- from kickoff to first value
- 5–7 weeks
- estimated payback*
- Month 3
- saved a year, estimated*
- $36k
* Estimates from the illustrative maths in chapter 07; we confirm your real figures in a discovery call.
- Industry
- Logistics
- Solution
- Route optimisation
- What we build
- Route optimisation
- People in control
- Every decision
- First value
- 5–7 weeks
- Payback
- Month 3*
The problem
Every wasted mile is paid for twice
Routes planned by hand or by habit add miles, fuel and overtime, and leave customers waiting. With dozens of stops a day there are millions of possible orders; no person can find the best one every morning.
- Routes are planned from memory or a spreadsheet
- Drivers double back across town
- Overtime when one van runs late
- Customers get wide delivery windows

Why we know it works
The approach is proven at scale
We build on methods that have already worked for large companies, and size them for a growing business. The evidence we draw on, as reported by UPS:
UPS built ORION, an optimisation system that plans each driver’s route from millions of possible stop orders. UPS reports it saves about 100 million miles and 10 million gallons of fuel a year, and that cutting just one mile per driver per day is worth up to $50 million a year across its fleet. ORION won the INFORMS Edelman Award for operations research.
- miles saved by UPS every year
- 0M
- gallons of fuel saved a year
- 0M
- a year from one mile less per driver per day
- $0M
UPS’s own figures from the rollout; UPS put the investment at about $250 million and the return at $300–400 million a year. Newer reporting puts fuel savings at about 9 million gallons a year.
See it work
The same day, planned two ways
An illustrative day for one van with ten stops. Switch between the route as it was driven and the route our optimiser plans.
Miles
48
Day
3 h 44
10 miles less on one van, one day: same ten stops, same customers.
How we solve it
Your data, an AI that understands it, and people in control
The same idea, sized for a growing business: we connect to what you already have, put the AI in the middle, and keep a person in charge of every decision that matters.
- 01
Your data
- Orders and addresses
- Delivery time windows
- Van GPS and capacity
- Live traffic
- 02
Route optimisation
A solver searches the possible stop orders for every van, with machine learning to predict how long each stop really takes.
- 03
Your workflow
Routes reach each driver’s phone every morning, and re-plan when an order is added or a van runs late.
- 04
Your people
The dispatcher approves the plan and handles the exceptions.
How we build it
First value in 5–7 weeks
One problem, a fixed scope and a clear plan. You see it working on your own data before it goes live.
DiscoverWeek 1
We ride along, map a typical day and collect a month of orders and GPS traces.
Connect the dataWeeks 2–3
We bring orders, addresses, time windows and vehicles into one place, with clean geocoding.
Plan and compareWeeks 3–4
We re-plan last month’s real days and compare the miles with what your drivers actually drove.
Go liveWeek 5
We put routes on your drivers’ phones, starting with a few vans.
ImproveWeeks 6–9
We learn real stop times and add live re-planning for the whole fleet.
What you need to start
Your orders and your vans
Route optimisation works on data you already have; no new hardware in the vans.
Orders with addresses
An export from your order system or ERP, with delivery windows where you have them.
Your fleet
Vans, capacities and shift times, and GPS traces if your vans already have trackers.
A dispatcher
Someone who knows the routes and approves the plan, especially in the first weeks.
Where the savings come from
The maths, line by line
An illustrative example with stated assumptions, so you can put in your own numbers. We confirm the real figures together in a discovery call.
$36k
saved a year, plus tighter delivery windows
A distributor running 15 vans
Illustrative · assumptions- Miles saved per van a day (assumption)
- 5
- Working days a year
- 250
- Running cost per mile
- $0.70
- Fuel and wear saved a year
- $13,100
- Driver time saved (15 min a van a day, $25/h)
- $23,400
The J-curve
A small dip, then compounding growth
Research on new technologies finds the same pattern: value dips while you invest in data, process and training, then climbs well past where you started. We keep the dip small by starting with one problem and paying back fast.
* Shape after Brynjolfsson, Rock & Syverson (2021); the payback month is illustrative.
What comes next
Where this is heading
- 01
Re-planning in real time
Routes that adjust themselves through the day as traffic, cancellations and urgent orders arrive.
- 02
Smarter loading
The same plan decides how each van is loaded, so the first stop is at the back door.
- 03
Precise arrival times
Customers get a narrow, reliable window, and fewer “where is my order?” calls.
Facing the same problem?
A free consultation maps where this would pay back fastest in your business.
Sources

Next case study · Finance & admin
Documents that read and file themselves
Let's build what's next for your business.
Tell us what's slowing you down. We'll show you where AI, automation, software and data will make the biggest difference, and what to do first.
- Free consultation
- Your workflows reviewed by a specialist
- Clear next steps, no commitment
Working across time zones · Live
- ----San Francisco
- ----New York
- ----London
- ----Dubai
- ----Sydney