How Conex is building enhanced customs: in-house AI, interoperability and human control

Our previous article introduced the concept. Enhanced customs is no longer a theoretical idea: several software providers are now building the tools that make it possible and they are not all making the same choices. This article sets out the technical and methodological convictions that guide the Conex approach and why they matter to customs clearance professionals.

Choosing technological independence

Conex develops its key building blocks in-house. EDI, blockchain, AI models: everything is designed, integrated and maintained by Conex teams. This means Conex controls every critical component, and business knowledge stays with the people who build the tools with no external integrator in between.

This choice comes at a cost. It also has direct benefits for the client.

 First, control over the roadmap. When a regulatory change comes along (a new ICS2ICS2 (Import Control System 2) is the European Union's IT system for transmitting pre-customs clearance declarations for goods imported from third countries. ... format, a pre-clearance obligation, a change to a national nomenclature) a provider that builds its own components can adapt its tools without waiting for a third-party supplier to react. It is a matter of days.

Second, depth of business knowledge. Conex is a pure-play customs specialist. Whereas most European players are supply chain generalists who have added a customs module to their catalogue, Conex focuses its efforts entirely on customs. This anchoring changes the very nature of the tools in its customs clearance software suite: their accuracy, their regulatory granularity and their ability to handle atypical situations.

Finally, continuity. Project management, development, deployment, support: everything goes through Conex. Rather than a chain of intermediaries, the client has a single point of contact.

AI that serves the declarant: human control comes first

Our previous article set out the principle: AI augments the declarant; it does not replace them. For a software provider, this is not a slogan, it commits the way we design our tools.

In practice, this translates into four choices.

The professional sets the rules; the agent applies them. No critical decision is delegated to AI. Business rules (applicable tariff preferences, control thresholds, origin conditions) are defined by the professional. The agent applies them within the framework it has been given.

Every AI suggestion is subject to human validation. No classification applied silently. No data extracted and injected without checks. At every sensitive step, the declarant validates, corrects or rejects.

No black box. Every proposal from the agent comes with the reasoning behind it: sources consulted, rule applied, confidence level. Traceability is built into the very structure of the system.

It is in this spirit that Conex chose to give its AI agents, ALBA & LEO, a persona, as a reminder that they are identifiable assistants with a clearly defined scope, not anonymous algorithms.

Customs interoperability and CDMS agnosticism: integrating without replacing everything

A customs department that wants to move to enhanced customs should not have to overhaul its entire infrastructure. This conviction guides the architecture of Conex tools.

First principle: CDMS agnosticism. Conex solutions plug into any existing ecosystem without requiring anything to be replaced, whether the client uses the Conex CDMS or another customs management system. No forced migration, no manual reconfiguration.

Second principle: modularity. Each product works on its own and can be combined with the others as needed. A customs department that wants to start with document extraction and keep its existing classification tool can do so. One that wants to activate everything can do that too. The move to enhanced customs happens at the client’s own pace.

40 years of regulation under our belt: the foundation of enhanced customs

Customs AI is only as good as the regulatory expertise behind it. Without that raw material, models classify nothing useful and extract nothing reliable. This is what sets apart a general-purpose AI plugged into customs from an AI designed within customs.

Conex has been building customs software for 40 years. Its knowledge is not limited to a single national market: its tools are deployed in France, Belgium, the United Kingdom, Ireland, Denmark, Spain, the Netherlands, Sweden and Norway. More than 2,000 customs departments across Europe are equipped with them.

What this depth brings to AI is concrete. Tariff classificationTariff classification involves assigning a code to a good in order to determine the applicable customs duties, taxes, and restrictions. ... does not depend solely on a product description, but on practice, case law, explanatory notes and the way rules are applied differently from one country to another. Document extraction does not depend solely on character recognition, but on understanding context: where to find a statistical value on a document from forwarder X in country Y, how to interpret a handwritten note, which inconsistencies to flag first. This kind of intelligence is built up over time, through years of real-world practice.

Choosing your enhanced customs provider: the four Conex pillars

• Technological independence.
• AI designed to serve the professional.
• Interoperability with existing systems.
• Regulatory depth.

These four pillars underpin the Conex approach to enhanced customs. They answer a question every customs department will eventually ask itself: who should we trust with the tools that will support the transformation of our profession?