The read-out. What the engine did, and how it landed.
Every decision the engine takes is a data point. Fleet analytics is where those points become the operational picture - what the on-time rate is, why it moved, which corridors are dragging, which riders are lopsided, which windows are systematically over-promised.
Five views that run themselves.
On-time delivery
Percentage of orders delivered inside their promised window, sliced by client, corridor, SLA tier, or hour of day. Trends over 7, 30 and 90-day windows.
Window accuracy
How often the predicted window was correct - not just whether the delivery landed. Systematic over-promising or under-promising surfaces here.
Rider utilisation
How much of a rider's shift was moving orders versus waiting at origin, idle, or off-route. Fairness bands highlight riders trending outside the fleet norm.
Reassignment outcomes
Every reallocation with its reason and its result - did it save the window, was the handover cost worth it, did the fleet get more balanced or less.
Corridor performance
Per-corridor deliveries, historical times, and outlier events. Corridors that are consistently missing windows get flagged for SLA or routing review.
Escalations
Every order the engine could not confidently promise - what happened, whether the dispatcher accepted the escalation, and how it resolved.
The point is not the dashboard. It is the decision.
Every headline metric drills into the specific orders behind it, and every order drills into the specific engine decisions that shaped it. If on-time drops on Wednesday, you can get to which corridor, which SLA tier and which rider before end of shift.
- Cohort-based comparisons - this week against the last four weeks, same shape
- Corridor and client filters at every level
- Exports to CSV for finance and SLA reporting
- Alerts when a metric drifts outside a configurable band
An honest read - one shift
On-time 94.2%
Against SLA target of 92%. Down 1.1 points from last Wednesday, up 0.4 from last month.
Corridor Bellary Rd
Contributed 2.1 points of the drop. Two windows missed by 3 min each due to a road closure between 17:20 and 17:45.
Reassignments
14 reassignments across shift. 12 saved windows, 1 broke even, 1 arrived late anyway. Reasons logged.
SLA review
Bellary Rd corridor flagged for a 3-minute window widening after 17:00 on weekdays. Suggested by engine, accepted by manager.
See it against your operation
The most useful conversation is with your own numbers. Book a working session and we will walk through the engine against a slice of your live shift.
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.