One live loop that runs across every order, every rider, every minute.
The delivery engine is five capabilities working together - not five separate tools you buy and stitch. Each page below explains what the capability does, how it gets its signals, and what to expect in the first month of running against your fleet.
Five capabilities. One live state.
Route optimisation
Rider paths continuously recalculated as new orders drop in, riders finish stops, and road conditions change.
Delivery-window prediction
Windows built from live traffic signals, current rider load, pickup queues at origin, and historical corridor times.
Dynamic rider reallocation
Orders reassigned to a closer or less-loaded rider the moment the decision improves the outcome for the whole fleet.
Live tracking and notifications
Customer-facing live status and dispatcher-facing fleet board, both driven off the same live state.
Fleet analytics
On-time rate, window accuracy, rider utilisation, batching efficiency and corridor performance over time.
The loop, honestly.
None of the five capabilities do the whole job alone. A route is only as good as the window it is promised for. A window is only as good as the reallocation that can save it. Here is how each signal moves.
Live loop
Order arrives
Origin, destination, parcel class and desired window flow in. Engine looks at every rider currently in the area with capacity.
Assignment scored
Each candidate rider is scored on distance, current queue depth, expected pickup delay at origin, and previous performance on that corridor.
Window predicted
The chosen rider's actual path is simulated against live traffic and pickup queue - a window is set that reflects reality, not a flat 30-minute promise.
State watched
Every rider position, every finished stop, every new order becomes an input the engine re-runs against. If a closer rider frees up, the assignment can move.
Reallocation
When reassigning improves the outcome (window at risk, faster path available, rider stalled), the order is moved and both routes are rebuilt.
Notify and log
Customer gets updated status; dispatcher sees the change on the board; analytics record why the reassignment happened for later review.
Show us your fleet size. Watch the swarm move at your scale.
Type a rider count and a rough daily order volume. The view on the right rebuilds to that scale, with a sample reassignment playing every few seconds - the same kind of decision the delivery engine makes for a live fleet.
An illustrative view based on typical patterns - not a live read of your actual fleet. Numbers move with your inputs so you can see the shape of the problem the engine solves.