Extract certificates of origin to structured JSON

Certificates of origin verify where goods were produced, enabling preferential tariff treatment under trade agreements. Formats vary by issuing body and agreement. Use Sensible to get structured certificate data for customs compliance, duty optimization, and trade documentation.

Why certificates of origin need specialized extraction

Country-specific formats, agreement-specific fields, and varied issuing bodies create diverse challenges.

Trade Agreement Variation

USMCA demands different fields than CPTPP or EU preferential certificates. Each trade agreement gets its own extraction configuration, capturing the specific preference criteria, blanket period, and certifier declarations it requires.

Multi-Format Issuing Bodies

Chambers of commerce, customs authorities, and exporters each issue certificates in their own format. The hybrid approach (LLM parsing for layout variation, SenseML rules for field validation) handles them all.

HS Code and Product Detail

HS codes, product descriptions, quantities, values, origin criteria: each line item is extracted with its full trade classification detail, enabling automated duty calculation and compliance checks.

Fields we extract

Trade agreement fields and product detail ship by default. Customize for your customs compliance workflow.

Parties

Exporter name/address, importer name/address, producer name/address, consignee, certifying authority, chamber of commerce

Product detail

HS tariff code, product description, quantity, weight, value, origin criterion, country of origin, invoice number/date

Certification

Trade agreement, preference criterion, blanket period dates, certifier signature, date of issue, certificate number


{ /* SenseML: certificate of origin extraction */
"fields": [
{
"method": {
"id": "queryGroup",
"queries": [
{
// Exporter name
"id": "exporter",
"description": "exporter name, exporter, certifier, producer"
},
{
// HS tariff code
"id": "hs_code",
"description": "HS code, tariff classification, harmonized code",
"type": {
"id": "custom",
"pattern": "[0-9]{4,10}\\.?[0-9]{0,2}"
}
},
{
// Country of origin
"id": "country_of_origin",
"description": "country of origin, origin country, goods originating in"
},
{
// Trade agreement
"id": "trade_agreement",
"description": "trade agreement, USMCA, CPTPP, preferential treatment"
}
// Additional fields for importer, product description, quantity, etc.
]
}
}
]
}
Generic Certificate of Origin

Standard chamber-of-commerce-issued certificate for international trade.

EUR.1 Movement Certificate

European Union certificate of origin for preferential trade agreements.

NAFTA/USMCA Certificate

North American trade certificate for preferential tariff treatment under USMCA.

Supported certificate types

Sensible processes certificates for USMCA, CPTPP, EU, ASEAN, and other trade agreements. New certificate formats from any issuing body can be configured to your customs compliance schema in hours.

By trade agreement

USMCA, CPTPP, EU-origin (EUR.1), ASEAN (Form D), GSP (Form A), generic certificates

By issuing body

Chamber of commerce certificates, customs authority certificates, self-certified (USMCA/CPTPP), notarized affidavits

Trusted by operations and engineering teams at

Common Questions

Answers about trade agreement support, HS code extraction, and issuing body formats.

Can Sensible extract HS codes from certificates of origin?

Yes. Sensible extracts Harmonized System (HS) tariff codes, product descriptions, quantities, weights, and values for each line item on the certificate.

What trade agreement fields does Sensible capture?

Sensible extracts the applicable trade agreement (USMCA, CPTPP, EU-origin), preference criterion, producer information, blanket period dates, and any certifier declarations.

Can Sensible detect signatures on certificates of origin?

Sensible detects signature presence and extracts the signatory name, title, date, and company when printed. Signature image extraction is not supported, but presence/absence detection is available.

Does Sensible handle certificates of origin from different countries?

Yes. Sensible processes certificates from various issuing bodies and countries. It extracts exporter, importer, country of origin, country of destination, and certifying authority regardless of format.

Do you support webhooks?

Yes. Sensible sends extraction results to your webhook endpoint when processing completes. You can also poll the API for status.

Does Sensible support human review?

Yes. Sensible flags extractions with low confidence for human review. You can configure review thresholds and workflows.

What security certifications does Sensible have?

Sensible is SOC 2 Type II certified and HIPAA compliant. Data is encrypted in transit and at rest.

How long is document data retained?

Document data is stored indefinitely by default. Custom retention policies are available and can be configured for same-day deletion if needed.

Is there a free trial?

Yes. Sensible offers a 14-day free trial on the Growth plan. No credit card required to start.

How is pricing structured?

Sensible uses per-document pricing for predictable costs. No token-based billing or usage surprises. Volume discounts are available for higher throughput.

How do I integrate with Sensible?

Sensible provides REST APIs and SDKs for Python and Node.js. Most integrations take a few hours. Webhooks, Zapier, and direct API calls are all supported.

What file formats does Sensible support?

Sensible processes PDFs (native or scanned), Microsoft Word (DOC, DOCX), spreadsheets (XLSX, XLS, CSV), single-page images (JPEG, PNG), multi-page images (TIFF), and email bodies with attachments.

How accurate is the extraction?

Accuracy depends on document quality and configuration. Most production deployments achieve 95%+ accuracy with proper validation rules and confidence signals.

How fast is document processing?

Processing speed depends on document size, page count, OCR requirements, and which extraction methods are used. Simple single-page documents process in seconds. Larger or more complex documents that use LLM-based extraction take longer.