Route optimization that reruns every time conditions change.
A fleet of 25 vehicles making 300+ daily stops plans routes the night before. By mid-morning, traffic incidents, reschedules, urgent additions, and weather make the static plan suboptimal. Dispatchers adjust manually throughout the day.
DHL benchmarks show AI route optimization delivers 12% reduction in transportation spend. McKinsey reports 10-15% fuel cost reduction and 15-20% faster deliveries for companies deploying AI. FourKites' Alan AI reduces manual scheduling workloads by 50%.
Enterprise optimization from Descartes, ORTEC, or Locus requires infrastructure and OR expertise beyond mid-market fleets. They need continuous optimization, not nightly batch runs.
This agent performs continuous route optimization. It starts with an overnight plan considering all constraints: delivery windows, vehicle capacity, driver hours-of-service, equipment, and priorities. Then re-optimizes throughout the day as conditions change.
Real-time feeds include traffic, weather, customer window changes, urgent pickups, and driver status. When conditions change, affected routes recalculate in minutes considering cascading impact on downstream stops and HOS constraints.
Dispatchers see recommendations they can accept or override. The system learns from overrides — if a dispatcher consistently rejects a routing decision, the model adjusts. Driver apps show updated routes with turn-by-turn navigation.
Built on Google OR-Tools with a FastAPI service layer, the agent pulls live data from telematics platforms (Samsara, Geotab) and traffic feeds, then re-solves the vehicle routing problem as conditions change throughout the day. Results are written back to your TMS and surfaced to dispatchers via a React Native interface with Mapbox routing overlays. Fleet-specific constraints — load limits, equipment types, driver certifications — are configured during a 3–4 week integration engagement. Redis handles sub-second route state for fleets up to several hundred vehicles.
The agent re-solves routing throughout the shift when traffic, weather, or schedule changes cross configurable thresholds. Recalculation runs in minutes, not hours, so dispatchers get updated routes before delays compound across the fleet.
Driver hours-of-service state is tracked in real time and fed directly into the constraint model — routes are generated that already respect mandatory breaks and daily maximums. Dispatchers receive pre-violation alerts before a driver hits a compliance threshold.
A single OR-Tools model simultaneously balances delivery time windows, vehicle capacity, fuel costs, equipment requirements, and driver skill assignments. Adding a new constraint type — a refrigerated cargo restriction, a bridge weight limit — is a configuration change, not a code change.
When dispatchers repeatedly override the agent's suggestions for a specific stop, area, or driver, those patterns update the model's soft constraints. This captures local knowledge — road conditions, customer preferences, access restrictions — that doesn't appear in any data feed.
Anonymized work with hard metrics — NDA-bound, no client names.
18%
Fuel Cost Reduction
96.5%
GPS Uptime
14%
Empty Mile Reduction
“The empty mile reduction paid for the system within the first two months of operation. The dispatch team now has real information to make decisions from instead of relying on driver phone calls.”
— Operations Director, Logistics Company
34%
Forecast Accuracy Improvement
61%
Stockout Reduction
23%
Overstock Reduction
“The stockout reduction was measurable within the first planning cycle. Category managers were sceptical initially, but the forecast accuracy on the products that had historically been hardest to predict won them over.”
— Head of Supply Chain Planning, FMCG Distributor
We custom-build each agent to fit your data, your rules, and your existing systems.
Free 30-min scoping call
Fordel Studios