Service · AI development for logistics

AI logistics optimisation. Practical projects, measurable gains.

We design, build and operationalise AI models that optimise your supply chain, from demand forecasting and inventory policy to pick paths, last-mile routing and customs flows. Not a full-stack replacement, but focused work on the flows where the biggest gains are.

OptimisationDemand & inventory
OptimisationWarehouse
OptimisationRouting & last mile
OptimisationDocuments & customs

Dutch logistics in numbers.

~9,4%
Share of logistics in the Dutch GDP
~770.000
Jobs in transport and logistics
~5.500
Logistics service providers
61%
Cite predictability as their biggest pain point

Source: CBS Transport & Logistics 2025, TLN Sector Monitor, Logistics Digital Index.

Excel forecasts and gut-feel buffers no longer hold up.

Most logistics organisations run on a combination of a good WMS, a solid TMS and, behind the scenes, a handful of Excel files where the real decisions are made. Forecasts are pulled into a spreadsheet, safety stock percentages sit in a forgotten cell, and the routes are adjusted by hand by a dispatcher with thirty years of experience.

That works. Until volume doubles, the SKU mix gets more complex, a second DC is added or purchase prices fluctuate yet again. Then forecast errors start to creep up, inventory costs turn out to be structurally too high, pickers lose half their day to walking paths, and last-mile costs rise faster than revenue.

AI models solve this differently from an even bigger spreadsheet. A good model learns from six seasons of historical data, factors in promotions, weather effects and macro signals, and produces a specific forecast per SKU per DC rather than one average line. Our role as enterprise AI implementation partner is to build and validate that model and integrate it with your existing WMS, TMS and ERP, so the output lands on the shop floor instead of disappearing into yet another dashboard.

What we don't do: deliver a platform you can never leave. We work in your cloud tenant, with your data warehouse, using model artefacts that you own. If you no longer need us in a year's time, the model keeps running — your own team can take it over. That's a different starting point from a large suite vendor that would rather have everything bolted together.

We focus on organisations that want to buy optimisation as a standalone service: 3PL and 4PL providers, retailers and e-commerce companies with their own DC, manufacturers with supply chain complexity, fulfilment partners, cold-chain logistics and importers/exporters with customs flows. Our pragmatic approach suits organisations that want concrete gains on one or two flows, not an ambitious multi-year project that tackles everything at once.

Optimisations we deliver as a service.

Each type of optimisation has its own model family, its own data requirements and its own integration pattern. Below is what we typically build per discipline — most clients start with one project and expand once the value has been proven.

Demand forecasting and inventory optimisation

The biggest and most rewarding optimisation for most clients. We build ML models for demand forecasting per SKU, per DC, per channel — with seasonal patterns, promotions, weather and macro features as input. The forecast passes through a second layer that calculates safety stock, replenishment and recommended reorder points based on your service-level targets.

The output lands directly in your ERP or purchasing tool, with confidence intervals so planners know where the model is certain and where manual adjustment makes sense. We add multi-echelon optimisation if you have multiple inventory tiers (central DC + regional hubs + stores).

For the warehouse layer, we build slotting models that assign items to locations based on turnover, weight, combined orders and seasonal effects — not a single fixed layout. Pick paths are calculated dynamically per order and shown on the handheld. For routing and last-mile, we connect an optimisation engine to your transport management system, where we can include cost, time and CO₂ as a combined objective. For customs and freight flows, we use document AI: consignment notes, invoices, T1 documents and commercial invoices are automatically read, checked and passed on to your customs declaration.

Finally, anomaly detection is an underexposed but powerful application: a model that continuously scans the event stream from your WMS, TMS and ERP and raises an alert when something deviates — a shipment that doesn't arrive where expected, a receipt that differs from the PO, a stock count that doesn't match the pick profile. Not a prediction, but immediate signal value for the control tower.

  • SKU-level forecastPer item, per DC, per channel — no ABC averages.
  • Dynamic safety stockBased on actual forecast error per SKU, not a single rule.
  • Multi-echelon allocationCentral DC, regional hubs and stores in a single optimisation.
  • Promotion and weather effectsExternal signals are factored in, not averaged out.

Built within the frameworks that matter.

We build in compliance, data ownership and governance from sprint 1. An AI model that can't get past your DPO, security officer or accountant is not an option in logistics.

EU AI Act

Risk classification and governance

For AI features in planning, labour allocation or, for example, picker performance models, we map out the risk classification under the AI Act, document the governance and ensure human decision oversight where it is mandatory. Pure flow optimisation (routing, slotting, forecasting) generally falls under a lighter regime, but we determine that distinction up front rather than discovering it later.

GDPR & data ownership

Your data stays your data

Models run in your cloud tenant or in our hosted environment under a data processing agreement. We never train on customer data without explicit consent, and there is no vendor lock-in on the model artefacts. When an engagement ends, you receive the model code, weights and pipelines so your own team can carry on without us.

ISO 27001 & NIS2

Security in the pipeline

Data pipelines, the model registry and inference endpoints are set up following ISO-compliant processes. For clients in NIS2 essential sectors, we build monitoring and audit logging to match. Access to production models runs through your SSO, with an audit trail per inference call if you want one.

CSRD & CO₂ reporting

Optimisation with sustainability as a KPI

Routing and network models can take cost and CO₂ as joint objectives. Output is CSRD-reportable, with insight into the trade-offs between the cost optimum and emissions reduction. For shippers with scope 3 reporting obligations, this is increasingly a hard requirement for their carriers.

MLOps discipline

Models that don't quietly degrade

Drift detection, automatic retraining, A/B tests when replacing a model, and a retraining window that fits your seasonal pattern. A model in production has a lifecycle, not a go-live date. We build dashboards that let your data team see continuously how the model is performing compared with previous periods.

Alongside your existing supply chain stack.

We don't replace your WMS, TMS or ERP. We connect our models to what you already have running and make sure the output lands where your teams work.

SAP
ERP & IBP
Microsoft
Dynamics & Fabric
Boltrics
WMS for 3PL
Manhattan
WMS & TMS
Transporeon
Carrier platform
PortBase
Port supply chain Rotterdam
Snowflake
Data warehouse
Databricks
Lakehouse & MLflow

The model doesn't live in a dashboard, it lives on your shop floor.

A forecast that is only visible in a BI tool is rarely used. We integrate our models directly into the system where the action happens: replenishment proposals in your ERP, optimal pick paths on your WMS handhelds, route suggestions in the driver app, anomaly alerts in the control tower's Teams channel.

For the foundation underneath, we often rely on a data engineering platform that we can build separately or connect to what you already have in place. The combination of data layer plus models is what makes the difference between a pilot and a production project. We work just as well with clients who run everything on Azure or AWS as with those on Google Cloud, and we have patterns for on-premise inference for data that cannot leave the organisation.

For shippers and carriers, the broader context of AI in the supply chain is also relevant. Our analysis of AI in transport covers the transport and network perspective, while this page is specifically about logistics optimisation as a service: what you can buy from us as a concrete engagement rather than as a platform licence.

Not sure about a large project yet?

Test your idea first: a working prototype in 1 day

With OneDayBuild, we make your idea tangible in a single day for €1,150, so you know whether further development is worth the investment. Decide to go ahead with the full build? Then we deduct the cost in full.

View OneDayBuild →

From audit to continuous improvement.

Every optimisation engagement goes through the same five phases. No lengthy preliminary reports, just sharp scoping and a working model in your hands quickly.

01 · Audit

Supply chain mapping

A day on site with your operations and data team. We map data quality, KPIs, bottlenecks and current tooling. Result: a bottleneck report and an initial optimisation shortlist.

02 · Prioritisation

Use case business case

For each candidate optimisation: data readiness, expected impact and integration effort. We advise which single one to start with, not four at once. A one-pager per use case for your steering committee.

03 · Pilot

Greenfield model + benchmark

One flow, one DC, one product line. The model runs alongside your current way of working (shadow mode) and is compared on hard KPIs over several sprints.

04 · Rollout

Production integration

The proven pilot is integrated into your WMS, TMS or ERP. It is rolled out in phases per DC or region, with training for planners and operators and a fallback path if something doesn't work.

05 · MLOps

Continuous improvement

Drift monitoring, retraining, quarterly reviews of KPI trends, and expansion to the next use case on the roadmap. Knowledge transfer to your data team where desired.

Work for logistics organisations.

Three types of projects that show the optimisation approach in practice. Every case starts with the same audit phase and ends with integration into the existing supply chain stack. The optimisation itself differs per type of flow.

E-commerce DC · Demand forecast

SKU-level forecasting for a multi-channel retailer

Replacement for an Excel-based flow. Forecast at SKU/DC/channel level, linked to the existing replenishment engine in the ERP.

Lower
forecast error on A-SKUs
Fewer
rush orders and stock-outs
3PL · Warehouse optimisation

Slotting and pick-path optimisation

AI-driven slotting per customer segment plus dynamic pick paths on the WMS handheld for a multi-shipper 3PL site.

Shorter
walking paths per order
Higher
picks per hour
Last mile · Routing optimisation

Routing and CO₂-aware planning

A routing model that treats cost and CO₂ as a joint objective, with deviation alerts for planners when actual execution strays too far from the planned output.

Fewer
empty kilometres
CSRD-
reportable CO₂ output

What the industry thinks.

Logistiek.nl trend report 2025

"AI-driven forecasting and multi-echelon optimisation are moving from pilot to production. Specialist builders are gaining ground on classic APS suites among organisations that want to run targeted projects rather than a full-stack replacement."

EVO/Fenedex Sector Monitor

"Predictability remains the biggest pain point for shippers; companies that structurally reduce their forecast error gain margin without the purchase price having to fall."

E-commerce DC client survey

"Appfront's approach is very pragmatic: one flow first, one model, a hard benchmark. Only then rollout. No hundred-page report before anything is running."

Answers for the supply chain director who is optimising.

The questions we hear most often in a first conversation.

What is the difference from enterprise APS suites such as Blue Yonder, o9 or SAP IBP?
Enterprise suites often replace your entire planning stack and require a multi-year implementation with a large consultancy team. We do the opposite: one concrete optimisation as a service, alongside your existing WMS/TMS/ERP, with a custom model that connects to your data. For organisations that only want to improve the demand, slotting, routing or customs part, not the complete S&OP stack, that is cheaper, faster and more flexible. For those who really want to replace everything, a suite is still the right choice, and we will say so honestly. Also read our analysis of AI in logistics for the broader context.
How much historical data do we need for demand forecasting?
For a serious seasonality-sensitive model, two to three years of transaction data is a healthy start, because it lets us see at least two full seasonal cycles plus a comparison year. Less is possible, especially if external features (weather, macro, promotions) are readily available. For new SKUs we use cold-start techniques that draw on comparable items. The audit phase always begins with a data readiness check so you know up front whether the foundation is sound.
Does this work alongside our existing WMS or TMS?
Yes, that is explicitly our starting point. We integrate via the APIs and messaging of your WMS/TMS (Boltrics, Manhattan, Centric, custom middleware, it makes no difference to us) and make sure the model output lands in the right place: replenishment proposals in the ERP, pick paths on the handheld, route suggestions in the driver app. For clients who also want to modernise or rebuild their WMS, we refer to our WMS warehouse software page, but that is a separate project.
What quick wins can be up and running within a few sprints?
In practice we see three common quick wins: a document AI flow for customs documents or consignment notes (faster to set up because the data requirements are narrower), anomaly detection in supply chain events (no model training on transaction data needed, only log streams), and pick-path optimisation within a single location where the WMS data is already clean. These are pragmatic pilots that deliver a working result within a few sprints. Demand forecasting and multi-echelon optimisation are more valuable but take a longer, multi-sprint project, mainly on the data side.
What does the AI Act mean for workforce planning or performance models?
Models that directly affect task allocation, shift estimates for employees or performance assessment fall into a higher risk class under the AI Act. That means mandatory risk classification, documentation, human review of critical decisions and transparency towards those affected. We map this out from the design stage, deliver the governance documentation and build in human-in-the-loop where required. For pure optimisation of physical flows (routing, slotting, forecasting) the risk class is usually lower, so lighter requirements apply.
What does a project like this cost?
An initial audit and use case prioritisation is a clearly defined preliminary phase with a fixed budget. The pilot that follows is scope-driven: one flow, one model, a hard benchmark. Only after the pilot results do we decide together whether and how the rollout proceeds. We work with fixed sprint budgets and give a concrete quote as soon as the scope is clear. An initial, no-obligation conversation about your situation is always free; costs only start once we actually begin work.
How do the scope of a pilot and a full rollout differ?
In the pilot we deliberately keep the scope small: one DC, one product line or one route segment, with a clear yardstick. The goal is to prove that the model delivers value in your context, not just on a clean test dataset. The rollout phase then covers integration with production systems, change management for planners and operators, and rollout to the other DCs or flows. After a successful pilot, many clients choose to run a second pilot in a different part of the chain before rolling out more widely, and we are happy to follow that sequence.
What is your approach to data ownership and exit?
All models, weights, code, pipelines and documentation belong to you. When a collaboration ends, you receive the artefacts in a form that your own team or another party can continue with. We work in your cloud tenant or in a hosted environment under a data processing agreement, not in a platform-as-a-service construction where you cannot continue without us. That sounds obvious, but in this market it is the exception rather than the rule.
Do you also do general AI strategy, or only building?
Both. For organisations that are still early in their AI journey, it often starts with strategy, prioritisation and a roadmap, which is a shorter, more conceptual project. Our enterprise AI implementation page goes into more depth on that side. For logistics organisations we often find that the strategy phase can be more compact than in other sectors: the valuable use cases (forecasting, slotting, routing) are fairly well known, so we can move quickly on to prioritisation and the first pilot.

Talk to us about optimising your logistics with AI?

A half-hour conversation with your supply chain director or operations manager. We listen, ask questions about your flows and data, and give you an initial direction on where the value lies. No obligation and no sales pitch.

Edit content