Reduce travel time by 20–30%, maximise crew productivity and deliver on time. CoPlaid combines configuration, a constraint-solving scheduling engine and real routing intelligence to produce routes your crews can actually run.
Route optimisation is only useful when it reflects how your operation actually runs. Each layer exists so the answer holds up in the field rather than only on paper.
Operations managers set the parameters that drive optimisation — break times, maximum jobs per route, travel buffers, shift-specific speed profiles, fleet counts per shift and time capacity limits — and save them as reusable profiles.
Job data is geocoded, frequencies expanded across the horizon, locations clustered, drive times built and routes solved against every constraint — then rebalanced so no vehicle is crushed while another runs half empty.
Real drive times over actual road networks, batched and parallelised for large job sets, cached for recurring runs, resilient to network hiccups, and matched to vehicle type through routing profiles.
Every business runs differently. These are the constraints that make the difference between a theoretical route and one a crew can complete.
An optimisation run is a pipeline. Each phase narrows the problem so the solver spends its time where it changes the answer.
Raw job data becomes a structure built for routing: locations geocoded, time windows converted to minute-based schedules, and service frequencies expanded across the horizon with each instance uniquely identified by date.
Machine-learning clustering groups nearby locations, cutting computational complexity while keeping route assignments geographically sensible. Clustering adapts to available vehicles and job density.
Precise travel times between all locations via professional routing services — real road networks and the actual routes drivers take, never straight-line approximations. This matrix is the foundation for every decision that follows.
Jobs are pre-assigned to vehicles from geographic proximity, crew size requirement, shift preference and capacity limits — creating a feasible starting point rather than making the solver find one.
The core engine solves the Vehicle Routing Problem with Time Windows, weighing time windows, capacity, service durations, shift boundaries and depot requirements together, escaping local optima to converge in roughly five to ten minutes.
A balancing phase redistributes jobs towards ~80% utilisation, preventing overloaded routes while eliminating near-empty ones — moving work only where constraints still hold.
Daily route assignments with sequenced job lists · travel time and distance per route · workload summaries showing capacity utilisation · unscheduled job reports · interactive map URLs with turn-by-turn navigation · exportable CSV schedules for field deployment.
If your operation runs on NetSuite, the whole route optimisation console can live there. A SuiteScript bundle renders it inside NetSuite's own UI shell — header, global search and navigation menu all stay put — so planners work without a second login or a second tab.
A matching console covers Messaging, installed the same way with its own key. See it here.
This is what renders inside the Suitelet — the same console whether it is opened from NetSuite's navigation menu or from the CoPlaid app, with NetSuite's own header and menu around it.
Sample data — fictional account names.
These steps run in order — each depends on the output of the one before it.
Create or select a route configuration template and upload a CSV of job details — addresses, service durations, crew requirements, time windows and frequencies.
Define when optimisation runs — specific dates, or a recurring schedule such as every Monday and Thursday for the next month — and initiate it.
The request is acknowledged immediately. Configuration and job data are stored securely and the scheduling engine is invoked with all parameters.
Over several minutes the engine processes thousands of route combinations, clusters geographically, calculates travel times and improves assignments iteratively.
Routes are stored and surfaced with summary statistics — total routes, jobs scheduled, distance travelled — with drill-down into each route and export for distribution.
Every route carries an interactive map showing the full path with stops in sequence, so managers validate geographic sensibility and adjust where needed.
Finalised routes export as CSV or integrate with mobile workforce management tools, so crews follow optimised schedules throughout the shift.
Every route respects time windows, crew requirements, shift boundaries and vehicle capacities. Nobody has to verify by hand that the plan is legal before it goes out.
Drive times use actual road networks and realistic speeds rather than straight-line estimates, so the schedule a crew receives is one they can genuinely complete.
These ranges reflect results seen across deployments and depend on fleet size, job density and how routes were planned beforehand. We will size the expected gain against your own job data before you commit to anything.
The platform runs on constraint programming solvers, machine-learning clustering, professional routing APIs and scalable cloud infrastructure — designed for high availability with automatic failover, comprehensive error handling and detailed audit logging.
It scales from a single-location business to multi-depot, nationwide operations with thousands of daily service appointments.
A 100-location run is split into chunks, processed in parallel and reassembled into one complete distance matrix.
Frequently requested location pairs are cached, cutting API calls and speeding up recurring runs.
Automatic retry with exponential backoff and multiple connection strategies handle congestion gracefully.
Routing profiles match the vehicle — car, truck or specialised service vehicle — so estimates reflect reality.
Ordering stops is one constraint. A real schedule also has to respect when each site will accept a visit, how long the work takes, whether it needs one person or two, which shift it belongs to, and when the vehicle must return to the depot. CoPlaid solves those together as a vehicle routing problem with time windows.
No. Travel times come from professional routing services over the actual road network, accounting for road layouts and the routes drivers really take. Straight-line estimates produce schedules that fall apart in the field.
Runs range from around ten jobs to a thousand, across daily or multi-week planning horizons, without performance degradation. Large job sets are clustered geographically and their routing requests batched and processed in parallel.
They are reported as unscheduled with the run rather than dropped or forced into a route that breaks a constraint, so you can see immediately whether the plan is complete.
Yes. Every route can be reviewed on an interactive map before release and adjusted where local knowledge beats the model. The optimiser produces a plan for a person to approve, not an instruction.
Yes. A Suitelet renders the Route Optimisation console inside NetSuite's own UI shell, giving access to route planning, scheduling, optimisation and run history without a separate CoPlaid login. It installs from the same bundle as the messaging console and uses its own scoped console key.
We will run it through the optimiser against your real constraints and show you the routes it produces beside the ones you ran.
