Country-of-Origin & Transshipment Risk Checker avatar

Country-of-Origin & Transshipment Risk Checker

Pricing

$150.00 / 1,000 origin risk analyzeds

Go to Apify Store
Country-of-Origin & Transshipment Risk Checker

Country-of-Origin & Transshipment Risk Checker

Screen a supply-chain / BOM document for US country-of-origin risk: extract components, origins and processing with verbatim quotes, then flag transshipment / origin-laundering red flags, assess substantial transformation, and list the reasonable-care evidence gaps a CBP audit would target.

Pricing

$150.00 / 1,000 origin risk analyzeds

Rating

0.0

(0)

Developer

Derrick

Derrick

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

9 days ago

Last modified

Share

What it does (for agents & pipelines): give it a supply-chain / bill-of-materials / manufacturing document as text or a public URL/PDF, and it returns a structured country-of-origin risk screen — components and their origins, processing steps, and the claimed origin (each with a verbatim quote), plus a deterministic transshipment / origin-laundering red-flag scan, a substantial-transformation assessment, the reasonable-care evidence gaps a CBP audit would target, and an overall risk level. Machine-readable, pay-per-document, no seat license.

Returns, as structured JSON:

  • Components + stated origins, processing steps + country, and the claimed origin — each with a verbatim source_quote, nothing invented
  • Transshipment red flags — mere repackaging/relabeling, minimal/simple assembly, third-country routing, "Chinese components merely assembled abroad", and explicit duty-avoidance language — each with severity and a plain-English why (the customs-fraud exposure)
  • Substantial-transformation assessmentsupported / weak / unsupported / undetermined, from the new "name, character, or use" signals vs. minimal-operation signals
  • Reasonable-care evidence gaps — the documents CBP expects you to hold (component BOM, process description, value/cost breakdown, tariff-shift classification, manufacturer's affidavit, mill test certificate for steel, smelt/cast certificate for aluminum, AD/CVD scope) that are missing from your file
  • ✅ An overall risk_level (low / medium / high), derived deterministically

Built for cross-border importers, sourcing/compliance teams, customs brokers, and trade-compliance agents who need to know — before entry — whether an origin claim is defensible and what evidence to assemble if CBP asks. This is the enforcement-defense angle, not FTA duty optimization.

Why the risk flags are trustworthy

The model only extracts components, processing steps, and the claimed origin with verbatim quotes. It never decides the risk level, never rules on substantial transformation, and never declares the legal origin. Deterministic code does all scoring from a curated rule matrix (rules/origin-rules.json) grounded in 19 CFR Part 102 (tariff-shift rules of origin), the "name, character, or use" substantial-transformation standard, and the importer's reasonable-care obligation. Every flag traces to a rule entry and a verbatim quote.

Input

{
"documents": [
{ "id": "sku-1", "claimed_origin": "Vietnam", "target_hts": "8544.42",
"text": "Components: copper wire (origin: China) ... assembled in Vietnam by simple assembly, then repackaged and relabeled as Made in Vietnam ..." },
{ "id": "sku-2", "url": "https://example.com/public-bom.pdf", "claimed_origin": "Mexico" }
]
}

1–20 documents per run. Provide text (paste the BOM + processing description — fastest and most reliable) or a url to a public page/PDF (fetched best-effort). Optional claimed_origin and target_hts are echoed back and used to detect foreign inputs.

Output (per document)

{
"claimed_origin": "Vietnam", "target_hts": "8544.42",
"transshipment_flags": [
{ "id": "mere-repackaging", "severity": "critical",
"matched_text": "then repackaged and relabeled as Made in Vietnam",
"why": "Mere repackaging or relabeling in a third country does NOT confer origin ..." }
],
"substantial_transformation": { "assessment": "unsupported",
"detail": "Only minimal operations ... on foreign inputs — this generally does NOT substantially transform the inputs ..." },
"evidence_gaps": [
{ "id": "bom-country-of-origin", "severity": "high", "label": "Bill of materials listing the country of origin of each component/material",
"why": "The foundation of any origin claim ..." }
],
"risk_level": "high",
"counts": { "components": 3, "transshipment_flags": 3, "evidence_gaps": 6 },
"disclaimer": "..."
}

vs. Thomson Reuters ONESOURCE / Descartes / supply-chain-risk platforms

These are strong enterprise tools — ONESOURCE Global Trade and Descartes automate FTA rules-of-origin qualification (can you claim a preferential tariff?), on annual, sales-led contracts. This Actor answers the opposite, enforcement-facing question: can you defend your origin claim and prove you didn't misdeclare? It scans for the transshipment/origin-laundering patterns CBP targets and lists the reasonable-care evidence gaps — pay-per-document, API-first, no subscription. If you want enterprise FTA-qualification and duty optimization, use ONESOURCE/Descartes. If you want an automatable transshipment-risk and evidence-gap screen you pay for by the document, use this.

Limits (read this)

  • NOT a legal origin determination, NOT customs or legal advice, and NOT a specific 19 CFR 102.20 tariff-shift result. It cannot clear or condemn a shipment. It documents defensibility and evidence gaps so you know where you stand and what to assemble.
  • The red-flag and substantial-transformation logic is heuristic pattern matching (v0.1) over the text you provide. It catches the common transshipment patterns and missing-evidence cases; it is not a substitute for a licensed customs broker / trade attorney and, where material, a binding CBP ruling.
  • Extraction is text-only and depends on document quality. Garbage in → low quote_hit_ratio → not billed.

Fair charging

Pay per successfully processed document (origin-analyzed). Failed fetches, non-supply-chain text, low-verification extractions, and documents skipped after your run's charge limit is reached are not charged. Every source_quote is re-verified verbatim against the document before the run is billable.

Development

pnpm install
pnpm typecheck # tsc --noEmit
pnpm test # vitest: rules table, validate layer, risk scoring
pnpm smoke # offline end-to-end (no network, no LLM)
pnpm golden # real-LLM acceptance vs hand-labeled supply-chain samples (needs DEEPSEEK_API_KEY)

Architecture (single-direction deps): main → fetch/extract/validate/match → rules → domain. Same three-layer engine as the GovCon clause extractor; the transshipment / reasonable-care rule matrix is the moat.

Current-source verification

Rule matrix grounded in primary sources retrieved 2026-07-18: tariff-shift rules of origin — 19 CFR Part 102; substantial transformation "new name, character, or use" — ITA / trade.gov; importer reasonable-care obligation — CBP Informed Compliance; binding precedent — CBP CROSS.