What the client needed
We built a machine-learning dispatch engine for foodpanda.
Our role: technology provider for the modules, backends, apps and services described here.
Outcomes +Delivereddispatch engine
What was built
- Machine-learning dispatch engine
- Order-to-rider assignment
Where the AI works
Dispatch modelMachine learning assigns each order to a rider.
Related capabilities
How the system fits together
Machine learning · Dispatch. The drawing shows the main parts and how work moves between them.
What retail and logistics projects demand
Routes change every hour
Dispatch and route planning run on live orders.
Stock is counted in hundreds of thousands
Inventory systems are built for large catalogues.
Someone must prove the handover
Custody records show who held a parcel, and when.
How we ran it
Working software every two weeksIn your environment, not on a slide.
One delivery leadA certified lead who owns scope, time and quality.
Written scopeWhat is in, what is out and what it costs.
Security from the first sprintISO/IEC 27001 controls on every build.
Related work
Private LLM
Language models running inside government networks
2deployments on client infrastructure
Document AI
AI that reviews documents for a mobile financial service
Mobile financial services provider
AI route planning
A sales and distribution app with AI route planning and data bots
32%more sales volume in 6 months

Predictive AI
A platform that predicts customer service needs
62%fewer support calls
