Customs AI stack · free pilots

Explainable AI for customs
and trade compliance.

From raw supplier spreadsheets to HS / TN VED codes with GRI reasoning and certification flags — and, for enterprise teams, search over released declaration archives. Built for a person who has to defend the output, not just receive it.

For enterprise teams: scoped pilot on redacted samples, NDA, API discussion case-by-case.

Illustrative output — current bot response format
Input
“LED desk lamp, 10W, USB-C, touch dimmer”
HS / TN VED
9405 42 390 0
Confidence
0.86
GRI trace
  • Rule 1 → Heading 9405 (lamps and lighting fittings)
  • Rule 6 → Subheading 9405.42 (LED, electric)
Certification
EAEU TR 004/2011: mandatory declaration of conformity
Sources
  • · EAEU TN VED, Chapter 94
  • · TR CU 004/2011, Annex 1

The problem

Classifying a single code is easy. Doing it at scale, defensibly, is not.

Supplier data arrives as a mess

One supplier sends Excel, another CSV, a third a PDF or a photo of a packing list. Half the descriptions are in a foreign language. Classification can't start until someone cleans it up by hand.

Classification has to be defensible

"Looks like this code" is not enough when a customs officer, auditor, or compliance manager reviews it. You need the GRI reasoning, the tariff references, and a confidence you can argue about.

Certification rules are invisible in the spreadsheet

Whether an item needs a mandatory declaration of conformity under EAEU TR 004, TR 020, or nothing at all — that's buried in regulations, not in the supplier's file. Miss it, and the shipment stops at the border.

What the stack does

Six capabilities. Four live today, two in scoped partnership.

01Live

Normalize supplier spreadsheets

Excel / CSV / PDF / photos in, a single reviewable schema out. Foreign-language descriptions translated, attributes extracted, duplicate rows merged, declaration-ready fields prepared.

02Live

Explainable HS / TN VED classification

Each row gets a code with a GRI 1–6 trace, confidence score, and source references. Today EAEU TN VED. The reasoning engine is HS-agnostic — adding another jurisdiction is a data question, not a rewrite.

03Live

Certification requirement detection

For each HS code, the system flags whether it falls under EAEU technical regulations (TR CU 004, 020, 025, etc.) and whether conformity is mandatory, voluntary, or not required. The output is a simple column — the reasoning stays traceable.

04Live

Telegram bot for quick lookups

One-off classification without any integration. Useful for on-the-fly checks, broker quick-turns, or evaluating reasoning quality before a scoped pilot on operational data.

05Pilot

Search over released declaration archives

Turn a team's historical DT archive into a searchable precedent layer: find similar past cases by meaning, not file name. Available as a scoped pilot on redacted samples.

06Roadmap

Declaration draft under R.055

A controlled next step, not a promise. From messy documents to a reviewable declaration draft, operator-in-the-loop. Interested teams should flag it early — this is a partnership, not a self-serve feature.

Who this is for

Built with four kinds of people in mind.

Importer ops lead

Spends hours cleaning supplier files before declarations can even start. Wants fewer Excel reshuffles, faster classification, and a repeatable process that doesn't depend on one senior expert.

Customs broker

Needs a defensible first-pass code with reasoning and precedent lookup. Treats the tool as a force multiplier for a small team, not a replacement for judgement.

Trade compliance manager

Owns the audit trail. Wants a consistent standard across the team, explainable outputs, and a clean answer on certification requirements before goods ship.

Platform / software vendor

Building a procurement, ERP, or logistics product and needs customs intelligence as an API. Interested in partnership and controlled deployment over a public signup form.

How this is presented

Before the pitch, the boundaries.

Not a replacement for a broker

Final responsibility stays with the qualified specialist. This is a copilot that prepares, explains, and accelerates — not a black-box declaration machine.

Honest about what's live

Anything in pilot or roadmap is labelled that way. No fake "already GA" on features still in design-partner build.

Data sensitivity

Enterprise pilots run on redacted samples under NDA. No supplier data, no declaration archive, gets used outside the scope of the pilot.

One person, one company

Scanovich is solo-founder work. That means fast iteration and a direct line to the builder — and it means pilots stay scoped to what one person can deliver well.

FAQ

Common questions

Is this only for EAEU / TN VED?
The classifier is live on EAEU TN VED because that is where the first users are. The architecture is HS-agnostic — adding another jurisdiction (EU CN, US HTS, UK Global Tariff) is a question of tariff data and test cases, not a rewrite.
What's the difference between the Telegram bot and a pilot?
The bot is a fast proof-of-quality: one description in, one explainable code out. A pilot runs on your operational data — supplier spreadsheets, a slice of declaration history — under NDA with agreed scope and success criteria.
How does certification detection work?
Given an HS code and product attributes, the system maps to relevant EAEU technical regulations and returns whether conformity is mandatory, voluntary, or not required. The mapping is traceable — you see which regulation and which annex drove the flag.
Do you replace the customs broker?
No. This is operator-in-the-loop tooling. The broker or compliance manager reviews every output, and their name is on the final submission. What changes is how much time they spend on preparation vs. judgement.
How does a pilot start?
Usually: a short call, a redacted sample (one supplier file or a slice of archive), agreed KPIs on time or quality, and an NDA. Pilots are free right now — signal over revenue at this stage.

Start with the bot. Continue with a pilot.

The Telegram bot is the fastest way to see the reasoning. When you're ready to run it on your operational data or a slice of your declaration archive, contact to scope the pilot.

Community Telegram: @ScanovichAI

Contact

Talk to us

Questions about pilots, partnerships, or deployment? We usually reply within a business day.

Direct

JST (UTC+9). Telegram — same day. Email — within 24h.