Route and transportation optimisation
Plans routes against traffic, weather, fuel, driver hours and service promise together, and replans when one of them moves.
- Moves
- Cost per delivered order
- Twin
- Logistics Twin
- Capability
- Optimisation
Industries
09 — Transport & Logistics
Every mile, priced against the promise.
Network design, fleet economics and service promise modelled as one engine — where a late load, an empty leg and a detention charge all resolve to cost per delivered order.
North Star
Cost per delivered order at promised service
The value engine, end to end
Discover → Model → Twin → Agents → Govern → Compound
The same six moves we run everywhere, expressed in the physics of this industry.
01
Discover
Where does the network lose money against the promise?
Cost-to-serve map by lane
02
Model
What drives lateness, empties and detention?
Causal network model
03
Twin
What happens if we redesign lanes or slots?
Network and fleet twin
04
Agents
Who replans and recovers in the moment?
Dispatch and exception agents
05
Govern
Are hours, safety and customs defensible?
Compliance control file
06
Compound
Does the lane still pay next season?
Outcome contract + lane monitor
Where the value is
Value pools and their drivers
Before a twin is built, we agree where the money sits and what moves it.
Value pool
Linehaul and routing
Driver
Empty miles, load factor, route quality
Measured as
Cost per mile delivered
Value pool
Service promise
Driver
On-time-in-full and recovery speed
Measured as
Penalty and lost-customer value
Value pool
Facility throughput
Driver
Dock, yard and labour synchronisation
Measured as
Detention and idle cost
Value pool
Documentation
Driver
Customs and freight paperwork handling
Measured as
Cost per shipment document
Use cases
Where value is already sitting in Transport & Logistics
Each one is a number somebody already owns, a twin that models it, and an agent that moves it inside a defined authority. Filter by function.
5 use cases
ETA prediction and exception management
Predicts arrival honestly, detects the shipment that will miss, and triggers the recovery while there is still time to recover.
- Moves
- On-time-in-full rate
- Twin
- Logistics Twin
- Capability
- Predictive + agentic workflow
Yard, dock and slot scheduling
Sequences arrivals and dock assignment against labour availability, cutting detention charges and idle bays at the same time.
- Moves
- Detention cost per load
- Twin
- Logistics Twin
- Capability
- Scheduling optimisation
Freight document and customs processing
Extracts and validates bills of lading, invoices and customs declarations, and clears the routine ones without a keystroke.
- Moves
- Cost per shipment document
- Twin
- Process Twin
- Capability
- Document AI
Damage and claims assessment from images
Assesses damage from photographs at handover, settles the small claims immediately and escalates only the contested ones.
- Moves
- Claim settlement cycle time
- Twin
- Process Twin
- Capability
- Vision models
Outcome twins
Twins, levers, features and the agents that run them
Each twin owns a set of levers. Each feature moves one lever. Each agent executes inside a defined authority.
Network Twin
Simulate lanes, hubs and slot design before committing contracts.
Levers
Empty milesLoad factorLane costHub throughput
Features
- — Lane simulation
- — Slot design
- — Carrier mix optimisation
Multi-agent layer
Planning Agent
Reoptimises the plan when demand or capacity moves.
Fleet & Asset Twin
Keep assets available where they earn, and maintain them before they fail.
Levers
AvailabilityMaintenance costFuel per mile
Features
- — Failure prediction
- — Maintenance scheduling
- — Driver-behaviour coaching
Multi-agent layer
Maintenance Agent
Books the intervention into the cheapest window.
Exception Twin
Detect the shipment that will miss and recover it while recovery is still possible.
Levers
On-time-in-fullRecovery costPenalty exposure
Features
- — ETA prediction
- — Exception detection
- — Customer communication
Multi-agent layer
Exception Agent
Triggers the recovery and tells the customer before they ask.
Claims Agent
Assesses damage from handover images and settles the routine.
Trade Document Twin
Clear the paperwork without a keystroke where the data is clean.
Levers
Document touch rateCustoms hold rateRework
Features
- — Document extraction
- — Validation against tariff rules
- — Hold prediction
Multi-agent layer
Customs Agent
Validates declarations and flags the ones that will be held.
Unit economics
ROI calculator — per feature, per unit
Set your volume, switch features on or off, and move each impact to your own evidence. Everything is expressed per delivered order.
Orders delivered per year
6,500,000
Contribution per delivered order
$2.7
Per-order economics; substitute per-load or per-TEU for freight-forwarding engagements.
Annual program investment
$3.5m
Network Twin
Unit cost — Cost per delivered order
5.0% — Fuel, hours, traffic and promise solved together.
$3.8m
annual value
Exception Twin
Leakage — Penalty and failed-delivery leakage
22.0% — Recovery starts before the miss, not after.
$1.9m
annual value
Network Twin
Unit cost — Detention cost per load
3.0% — Arrivals sequenced against labour actually available.
$2.3m
annual value
Trade Document Twin
Unit cost — Cost per shipment document
2.5% — Routine declarations clear untouched.
$1.9m
annual value
Exception Twin
Unit revenue — Revenue per order
1.5% — Reliable promises can be priced as promises.
$1.4m
annual value
Value by feature
Annual value contributed by each active feature at current settings.
Value and ROI vs volume
How engineered value and ROI move as orders delivered per year change. The marker is your current setting.
Cumulative value vs investment
Where the curve crosses the investment line is payback.
Value mix by lever
Which lever the engineered value is actually coming from.
Baseline contribution
$17.5m
Engineered annual value
$11.3m
ROI on program
224%
Payback
3.7 months
Directional model. In an engagement every number here is replaced by your measured baseline, signed off by finance, and written into the outcome contract before any agent goes live.
Scale
How this compounds from one unit to the enterprise
01
One lane / one hub
Prove cost-to-serve and OTIF on a bounded flow.
02
Region
Same twins, new lanes; carrier and customs rules parameterised.
03
Global network
Shared runtime, per-jurisdiction trade rules, one cost-per-order number.
Integrations
Domain platforms we connect
Vendor-agnostic by design. Connectors are added per engagement — no platform lock-in.
TMS / WMS
- Blue Yonder
- Manhattan
- SAP TM
- Oracle OTM
Telematics
- Samsara
- Geotab
- Trimble
- OEM fleet APIs
Data & cloud
- Snowflake
- Databricks
- AWS
- Azure
Trade & customs
- Descartes
- e-Customs gateways
- Carrier EDI
- GS1 networks
Regulations and standards
What we are held to in this industry
Compliance is a design input, not a review gate. Every agent action is logged, attributable and reversible.
Driver hours and tachograph rules
No optimisation may propose a plan that breaches hours.
Customs and export controls
Declarations, restricted parties, tariff classification accuracy.
Dangerous goods (ADR / IATA)
Hard constraints encoded, never learned.
GDPR
Driver telematics and behavioural monitoring proportionality.
EU AI Act
Transparency for automated worker-affecting decisions.
Standards supported
GS1EDIFACT / EDI 214ISO 28000ISO 27001NIST AI RMF
Next industry
Professional & Business Services