AN Alpesh Nakrani
SolutionsBlogBooksPraiseAbout Work with me ↗
Logistics · Compliance readiness

HTS classification that saves broker review time.

Produce evidence-grounded HTS candidates, ruling references, and an uncertainty record for licensed-broker review.

◆ human-gateda person approves every consequential action
$15,500
fixed-scope pilot
Enterprise / regulated launch
launch posture
High current buying momentum
market signal
customs-and-hts-classification-assistant
// normalize product facts
input: Product composition
step: identify missing discriminators
citations: [ source ✓ ]   confidence: 0.93
HUMAN GATEawaiting review →

Nothing is finalized until a human approves it.

Built for
The buyer
Chief Compliance Officer, VP Global Trade, customs-broker President
The champion
Licensed Customs Broker, Trade Compliance Director, Classification manager
Day-to-day users
Classification analysts, import specialists, product compliance teams

Designed, built, and evaluated by Alpesh Nakrani, VP of Growth at ViitorCloud, 14 years shipping software, writing on AI-Native engineering and evaluation.

Evals-first
built in from day one
Human-gated
judgment stays with you
The problem

Where the time and money actually go.

Product descriptions are incomplete, tariff schedules and rulings are complex, and exact 10-digit classification requires legal and product-context judgment.

Who feels it

Classification analysts, import specialists, product compliance teams

Trigger to act: Tariff volatility increases landed-cost risk, classification backlog delays entry, product catalogs are expanding, or an importer needs defensible review documentation.

Outcome & ROI

The result you can model before you sign.

Illustrative, replace with your data
$33,000
per month, illustrative

Illustrative only: 2,000 SKUs reviewed/year × 18 minutes removed × $55 loaded specialist hourly cost ÷ 60 = $33,000 annual capacity. Duty impact is classification-specific and cannot be promised.

The outcome, plainly: Produce evidence-grounded HTS candidates, ruling references, and an uncertainty record for licensed-broker review.

Top-k classification recall
exact-code agreement
evidence citation accuracy
How it works

Inputs in. A cited, review-ready result out. Your expert decides.

A Permission-aware RAG copilot. Every material fact is grounded in an allowed source and returned with its identifier, no invented data.

01
Normalize product facts
02
identify missing discriminators
03
retrieve headings, notes, and rulings
04
generate ranked candidates
05
explain reasoning
06
calculate uncertainty
07
prepare broker decision record
Reference architecturegrounded · human-in-the-loop · fully auditable
Source systems · scoped access
Product information system
trade compliance platform
HTS schedule and rulings corpus
broker workflow
ERP
Grounded reasoning core
Retrieve & extract
grounded on your sources, returns citations
Reason & draft
Claude Sonnet 4.6 or GPT-5.6 Terra
Human gateA licensed customs broker or authorized trade specialist selects the final code and filing treatment; high uncertainty always escalates.
Action · only after approval
prepare broker decision record
Audit trace
sources, rules, confidence, reviewer
Tenant isolation
minimum data, never cross-tenant
Evaluation suite
baselined pre-launch, watched after
Observability
cost, latency & drift telemetry
Model strategy

Claude Sonnet 4.6 or GPT-5.6 Terra for complex grounded work; select by task-level evaluation; Gemini 2.5 Flash, GPT-5.4 mini or Claude Haiku 4.5 for high-volume routing and drafting. PostgreSQL + pgvector or managed vector store; policy rules and evaluator service.

Inputs
  • Product composition
  • use/function
  • technical specifications
  • images
  • country of origin
  • prior classifications
The human gate

AI-Native, not autonomous. Judgment stays with your people.

The machine does the work; the human’s role narrows to the one thing that matters, judgment. That constraint is what makes it safe to deploy.

Non-negotiable human gate

A licensed customs broker or authorized trade specialist selects the final code and filing treatment; high uncertainty always escalates.

What it will never do
Assistant only, no autonomous customs filing
No legal opinion
No guaranteed exact 10-digit code
No suppression of uncertainty or contrary rulings
The scorecard

A scorecard, not a demo. We baseline what breaks in production.

Every deployment ships with an evaluation suite. These are the numbers we baseline before launch and monitor after.

Primary
Top-k classification recall
exact-code agreement
evidence citation accuracy
unknown/follow-up rate
reclassification rate
broker review time
critical false-confidence rate
Why this, not that

The category is crowded. Most of it isn’t built for your workflow.

The alternatives
Descartes CustomsInfoAvalaraThomson Reuters ONESOURCE Global Tradee2openSAP GTScustoms broker knowledge teams
This implementation

Fixed-scope, tuned to your systems and rules, grounded in your data, with the human gate and audit trail built in from day one. A price you own, not a subscription you rent.

✓ Fixed price, not a seat subscription ✓ Grounded in your data & rules ✓ Human approval on consequential actions ✓ Auditable decision trace
Systems & integrations

It plugs into the stack you already run.

No rip-and-replace. Access is scoped to the minimum data necessary, isolated per tenant, and fully logged.

Product information systemtrade compliance platformHTS schedule and rulings corpusbroker workflowERPdocument repository
Pricing

Transparent by design. The build price buys the workflow and the proof.

A fixed implementation fee plus a monthly bill that scales with volume and governance. No hidden seats.

Pilot
$15,500
one-time · bounded proof of value
  • One process / scope
  • Live workflow on your data
  • Baseline evaluation suite
  • Measured vs. current process
Most chosen
Production
$36,000
one-time · full deployment
  • Full scope & integration
  • Human-review UI & audit trail
  • Write-back to your systems
  • Production evals & monitoring
Enterprise
$58,000
one-time · multi-entity / regulated
  • Multi-facility rollout
  • Advanced security & compliance
  • Custom control & escalation
  • Dedicated evaluation program
Monthly operating cost

10,000–35,000 grounded questions/month plus indexing and vector search.

$500–4,200
usage (models, OCR, vector, storage)
$2,200/mo
managed evaluation & monitoring

Planning assumptions, not vendor quotations. Your product information system and other platform licenses are separate and owned by you. Figures confirmed during scoping.

On working with Alpesh
“His vast knowledge of technologies and a natural problem-solving mindset consistently lead us through complex challenges with clarity and confidence.”
AM
Adil Multani
Senior Backend Developer
Why this is safe to try
01Baseline first. We measure your current numbers before we build anything.
02Fixed scope, fixed price. One process in the pilot. No open-ended engagement.
03Expand only if the scorecard earns it. You see the measured result before committing to production.
04Your people stay in control. The human gate means nothing consequential happens without a human’s approval.
FAQ

Questions serious buyers ask.

Does the AI act on its own?

No. A licensed customs broker or authorized trade specialist selects the final code and filing treatment; high uncertainty always escalates. The system drafts and recommends; a human approves every consequential action. Explicitly excluded: assistant only, no autonomous customs filing; no legal opinion; no guaranteed exact 10-digit code; no suppression of uncertainty or contrary rulings.

How do you stop it inventing facts?

Every material claim is grounded in an allowed source record and returned with its source identifier. The system separates observed facts, model inference, and missing information, and routes to a human whenever confidence is low, evidence conflicts, or an adverse outcome is possible.

What does it cost to run each month?

A usage bill of roughly $500–4,200/month (10,000–35,000 grounded questions/month plus indexing and vector search), plus a $2,200/month managed retainer for evaluation, monitoring and maintenance. Your existing platform licenses are separate and already yours. Exact figures are confirmed during scoping.

Do we need a ChatGPT or Claude subscription?

No consumer ChatGPT or Claude subscription is required for the production workflow. The client needs an approved API/cloud billing account. Workspace seats are optional for internal prototyping and administrator access.

How is this different from Descartes CustomsInfo?

Tools like Descartes CustomsInfo, Avalara, and Thomson Reuters ONESOURCE Global Trade are broad platforms you adapt to. This is a fixed-scope implementation tuned to your systems and rules, grounded in your data, with the human gate and audit trail built in, and a transparent price instead of a seat subscription.

How long until it’s live, and how do we prove it works?

This is an enterprise / regulated launch. We baseline “Top-k classification recall” first, then measure against that baseline. You see the scorecard before expanding scope, the evaluation suite ships with the system, not as an afterthought.

Book a scoping call

Bring your real numbers. Leave with a fixed-scope plan.

A 30-minute engineering-led working session, no slideware. You leave with a sized opportunity estimate, a fixed-scope pilot plan, and the integration & human-review path mapped.

VP of Growth at ViitorCloud · senior delivery owner confirmed before paid work

Ask AI about Customs & HTS Classification Assistant