Trusted by companies in 15+ countries around the globe

  • adso
  • bollore
  • chef_me
  • dp_world
  • dsv_logo
  • g10
  • gulftainer
  • helllmann
  • momentum
  • nespresso
  • noatumlogo
  • northladder
  • rsa_global
  • rstg
  • sky_express

One platform for the decisions that move freight.

Orders, plans, tracking, billing, rules and the agents working on them. Click around: this is the product, with sample data.

Fero · interactive demo

Planning board

Thu · Dubai · 06:00–16:00Solve plan

Orders today

142

38 consolidated

Vehicles planned

36 / 41

5 spare

Avg. utilisation

88%

target 85%

Invoices audited

212

7 variances

06:0008:0010:0012:0014:0016:00

TRK-01

Reefer 10T

ORD-2231ORD-2236ORD-2244

TRK-02

Reefer 10T

ORD-2232ORD-2239ORD-2247

TRK-03

Dry 10T

ORD-2229ORD-2234ORD-2241

TRK-04

Dry 3T

ORD-2233ORD-2242ORD-2250

TRK-05

Dry 40FT

ORD-2230ORD-2245
Cold chain protectedUnplaced 0Empty km −12%

Interactive demo · sample data · press ⌘K inside

What we solve

Start where it hurts. Everything shares one data model.

Routes, schedules, loads and fleet mix, solved rather than guessed.

Compute-heavy solvers for the decisions that decide your margin: which vehicle, which driver, which order, which route, which carton goes where. Every plan is feasible by construction and explains anything it could not place.

  • Vehicle routingTime windows, capacity in several dimensions, pickup–delivery pairs, breaks and reloads.
  • Linehaul schedulingLegs assigned to vehicles and drivers together, respecting hours, docks and cold chain.
  • Load consolidationShipments on similar routes merged onto fewer vehicles, ranked by kilometres saved.
Explore Planning & Optimization
Planning & Optimization6 engines

How it works

AI where the world is messy. Algorithms where it has to be right.

Language models are good at reading. Solvers are good at deciding. Fero uses each for what it does best, with your rules and your people in between.

01Read· Language models

Every document, message and call becomes data.

Invoices, delivery notes, WhatsApp orders, emails and phone calls are read and turned into structured records. Anything ambiguous goes back as a question, not a guess.

  • PDFs, spreadsheets, email, WhatsApp, voice
  • Field-level confidence on every value
  • Matched to the order, contract or trip it belongs to
Gulf Line Transport LLC

Plot 42, Jebel Ali Free Zone, Dubai

TRN 100 4827 3319 0003

Tax invoice

No. TI-0184

Date 12/09/2026

Bill to

Consignee account 4471

Mussafah Industrial, Abu Dhabi

Reference

BK-22418 · T-2207

Payment 30 days

DescriptionAED
Line haul · Jebel Ali → Mussafah1,882.75
Fuel surcharge142.00
Detention · 2 hrs180.00
Documentation35.00

Subtotal2,239.75

VAT 5%111.99

Total AED2,351.74

Extracted

0/11 fields
  • Carrier—
  • TRN—
  • Invoice no.—
  • Date—
  • Bill to—
  • Line haul—
  • Fuel surcharge—
  • Detention · 2 h—
  • Documentation—
  • VAT 5%—
  • Total (AED)—

Illustrative

02Check· Rule engine

Your policies, enforced the same way every time.

Contracts, tariffs, dispatch guards and approval limits live as versioned rules. A missing or conflicting fact blocks the action, and every decision records the rule that made it.

  • Versioned and effective-dated
  • Fails closed when facts are missing
  • Every decision explainable and replayable

DISPATCH-REEFER v5

Evaluating trip T-2211 · on DispatchTrip

effective 01 Sep
  1. Leaving a port: customs must be clearedCUSTOMS_CLEARED
  2. Gross weight within port limitPORT_WEIGHT_LIMIT
  3. Weighbridge agrees with declarationDECLARED_VS_OBSERVED_WEIGHT
  4. Temperature reading is freshFRESH_REEFER_TEMPERATURE
  5. Temperature within set pointREEFER_TEMPERATURE_IN_RANGE

Evaluating…

0/5 conditions

replayable

Illustrative

03Solve· Optimisation

When the day changes, the plan is solved again.

Routing, scheduling, packing and consolidation run on real optimisation solvers. When a truck breaks down, work is reassigned in seconds, and anything that cannot be placed says exactly why.

  • Vehicle routing, CP-SAT scheduling, 3D packing
  • Hard constraints: hours, docks, cold chain
  • Proposals, never silent changes
Linehaul schedule
Plan live
T01
T02
T03
T04
T05
T06
—
0810121416
09:33
ReeferDryAt riskUnplacedIllustrative run

04Act· Agents

Agents carry it out. People approve what matters.

Agents create trips, notify drivers, chase milestones and raise invoices through the same API your team uses. Anything that moves money or commits capacity waits for approval.

  • Risk-tiered approval gates
  • Same permissions as the role they act for
  • Full audit trail

Activity

Plan P-0931 · Thursday

Executing
  1. SolverPlan proposed for Thursday

    07:38P-0931 · 11 trips
  2. RulesDispatch guards passed on all trips

    07:38DISPATCH-REEFER@5
  3. Approval

    07:42

    Plan P-0931 · 11 trips

    Approved by Operations

  4. AgentTrips created and vehicles assigned

    07:42T-2207 … T-2217
  5. Drivers notifiedWhatsApp · 11

    07:43

    Trip T-2207 · Thu

    Pickup JAFZA Gate 4 at 08:10 · 6 PLT → Al Quoz.

    Reply 1 to confirm.

    07:43

  6. AgentProof of delivery captured

    09:58ORD-2231 · POD
  7. AgentInvoice raised, matched to contract

    10:01INV-5520 · AED 1,420.00

Illustrative

Classical algorithms, compute-heavy

The maths does the deciding

Six optimisation engines sit under every Fero product. They search the space of feasible plans and return the best one they can find, with a reason for anything they leave out.

  • 01Trip planning

    Vehicle routing

    Sequences every stop across every vehicle so the fleet covers the day with the fewest tours and kilometres.

    MethodRich VRP · metaheuristic search (Rust)

    Time windowsWeight + volume capacityPickup–delivery pairsDriver breaks
  • 02Linehaul scheduling
    T1T2T3T4

    Constraint scheduling

    Assigns every leg to a vehicle and a driver at the same time, without double-booking either, and protects the cold chain first.

    MethodOR-Tools CP-SAT · interval model

    Driver hoursDock capacityOpening hoursTemperature class
  • 03Order splitting
    3T×410T×240FT×1

    Fleet-mix optimisation

    Chooses the cheapest combination of vehicle types that can legally carry a set of orders, and says how many of each.

    MethodInteger linear programming · branch-and-bound

    Per-type costWeight & volumeItem dimensionsVehicle availability
  • 04Load building

    3D load packing

    Places every carton in the truck or container, in three dimensions, and proves it fits before anyone loads it.

    MethodPivot-based 3D packing · knapsack ILP

    Six rotationsStackabilityCollision checks500–2,000 items per load
  • 05LTL → FTL
    2 SHIPMENTS → 1 TRUCK

    Route-similarity consolidation

    Finds shipments travelling the same way at the same time and merges them onto one vehicle, ranked by utilisation and kilometres saved.

    MethodFréchet-distance matching · parallel (Rust)

    Route shapePickup proximityTime-window overlapDetour tolerance
  • 06Replenishment
    FORECAST

    Demand forecasting

    Predicts what each site will need and when, so routes and capacity are planned for tomorrow's demand rather than yesterday's.

    MethodGradient-boosted trees · seasonal decomposition

    Order cadenceSeasonalityChangepointsOutliers
How the engines and agents fit together

In production

Built with operators across the Gulf, running every day.

15+
countries served
5M+
orders & shipments on TAME
21
ERPs & WMS connected
7
industries configured
  • ISO 27001 certified
  • Hosted on Microsoft Azure, UAE regions
  • AES-256 at rest · TLS 1.2+ in transit
  • Your data never trains anyone else's model

Bring us one lane. We will show you the difference on your own numbers.

A week of your orders, rates or invoices, run through Fero with your contracts and your carriers.