01
Inconsistent input
“Consulting,” “software services,” and “IT solutions” can describe very different establishments. Keyword matching is not enough.
Business activity,insurance-ready.
Turn a free-text business description into governed SIC and NAICS classifications—then connect it to Lloyd's industry sectors, segment risk scores, and relevant coverage and product candidates.
Classify business activities—not just keywords.
Free public demo; sign-in is required before the first search. Do not enter confidential or personal information. Open full demo
REST + JSONSIC 1987 + NAICS 2022Lloyd's CR1298 candidates7 segment risk dimensionsCoverage + product candidates
Insurance context is fragmented. Your workflow does not have to be.
Applicants and brokers describe the same business in different ways, while classification, market sectors, risk guidance, and coverage references live in separate systems. Facio connects those layers without blurring their provenance.
02
Disconnected references
SIC, NAICS, Lloyd's CR1298, and insurance product catalogs serve different purposes. Facio preserves those distinctions.
03
Hidden assumptions
A code alone hides ambiguity and risk assumptions. Confidence, provenance, and review states show what can automate—and what cannot.
One description. A connected insurance data layer.
Normalize the activity, classify it against governed taxonomies, and enrich the resulting segment with market, risk, and coverage context that remains traceable to its source.
Natural-language classification
Send the language your customer already uses. Facio identifies the primary activity, business model, products, services, and qualifiers.
Independent SIC & NAICS
Classify both taxonomies independently, preserve every hierarchy level, and use crosswalks only as compatibility evidence.
Lloyd's market context
Resolve a selected SIC activity to source-backed Lloyd's CR1298 industry-sector candidates, with confidence and review status.
Segment risk profile
Add seven versioned 1–10 property and liability risk dimensions to support triage and questions—not underwriting decisions.
Relevant coverage context
Surface core and conditional coverage packages plus source-backed NAIC/SERFF product candidates for human review.
Governed and auditable
Return confidence, alternatives, warnings, source references, and dataset versions. Candidate mappings are never presented as official.
From applicant language to governed insurance context.
Understand the activity
Separate the primary business activity from products, customer type, business model, and secondary activities.
Classify each taxonomy
Select server-validated SIC and NAICS candidates independently, preserving hierarchy, alternatives, and confidence.
Enrich the insurance segment
Attach the SIC segment risk profile, relevant coverage packages, and review-required insurance product candidates.
Resolve market references
Use connected lookups for Lloyd's CR1298 sector candidates and return provenance instead of implying an official conversion.
More than a taxonomy code.
The core response explains the classification and its confidence. Connected enrichment adds segment risk, coverage relevance, insurance product candidates, and Lloyd's market context with explicit provenance.
All codes are returned as strings, preserving leading zeroes and official formatting.
response.fields
primary.sic.code6411
primary.sic.hierarchy4 levels
primary.naics.code524210
primary.naics.hierarchy5 levels
primary.confidence0.97 · high
primary.sic.insurance.riskScores7 dimensions · 1–10
primary.sic.insurance.recommendedCoveragescore + conditional
primary.sic.insurance.naicProductCandidatesreview required
lloydsSectorCandidatesconnected lookup
review + warningsexplicit governance
versionstaxonomy + enrichment
Classification and enrichment built for insurance workflows.
Move from unstructured intake to connected industry and risk context without losing the original description, uncertainty, provenance, or audit trail.
01
Quote intake
Normalize the applicant’s own description before the risk reaches an underwriter.
02
Appetite & routing
Trigger questions, route submissions, or apply appetite rules with confidence thresholds.
03
CRM & bordereaux
Standardize legacy free-text records for consistent reporting and integrations.
04
KYB & onboarding
Enrich onboarding data while preserving source text and classification provenance.
05
Renewal cleanup
Reclassify historical descriptions through a reproducible, versioned process.
06
Portfolio analytics
Aggregate exposure by SIC division, NAICS sector, or leaf industry.
Automate when the evidence is strong. Review when it is not.
Facio does not force every input into a code. It distinguishes activity from occupation, exposes one-to-many relationships, and returns an explicit review state when evidence is incomplete.
- Versioned source data
- Candidate-constrained classification
- Calibrated confidence bands
- Alternatives and reason codes
- Review-required derived mappings
- No underwriting or coverage decisions
Review required
“Project manager”
An occupation is not enough to classify an establishment. What products or services does the business provide?
One classification response. Connected enrichment lookups.
Use predictable REST and JSON contracts for classification, then resolve governed Lloyd's and insurance reference data without collapsing distinct systems into an unreliable conversion.
REST + JSON
Predictable request and response contracts for modern application stacks.
Schema-first docs
OpenAPI definitions, typed examples, and clear error responses.
Auth & controls
API keys or OAuth, tenant quotas, and rate-limit headers.
Versioned results
Reproduce a result with the returned taxonomy and classifier versions.
{
"status": "classified",
"primary": {
"sic": {
"code": "6411",
"title": "Insurance Agents, Brokers, and Service",
"insurance": {
"scale": { "minimum": 1, "maximum": 10, "direction": "higher_is_riskier" },
"riskScores": {
"property": { "fire": { "score": 2 }, "burglary": { "score": 2 }, "water": { "score": 3 } },
"liability": {
"thirdParty": { "score": 3 },
"employersLiability": { "score": 3 },
"professionalLiability": { "score": 9 },
"productLiability": { "score": 1 }
}
},
"recommendedCoverages": [
{ "code": "THIRD_PARTY", "relevance": "core" },
{ "code": "PROFESSIONAL_INDEMNITY_FINANCIAL", "relevance": "core" },
{ "code": "CYBER", "relevance": "core" }
],
"assessment": { "status": "derived_estimate", "confidence": "medium" }
}
},
"naics": {
"code": "524210",
"title": "Insurance Agencies and Brokerages"
},
"confidence": {
"score": 0.97,
"band": "high",
"decision": "auto_accept"
},
"relationship": "many_to_one"
},
"review": { "required": false },
"warnings": [
{ "code": "INSURANCE_RISK_ESTIMATE", "message": "Segment guidance, not underwriting advice." },
{ "code": "NAIC_PRODUCT_CANDIDATES", "message": "Derived and review-required." }
],
"alternatives": [],
"versions": {
"classifier": "classifier_1.0.0",
"US_SIC_1987": "sic_1987_facio_2026_08_001",
"US_NAICS_2022": "naics_2022_facio_2026_08_001",
"insuranceRisk": "sic_insurance_risk_2026_08_23_002"
}
}SIC and NAICS are related—not interchangeable.
U.S. SIC remains common in insurance, finance, and legacy datasets. NAICS is the current North American statistical standard. Facio classifies both systems independently and returns relationship provenance.
| System | SIC | NAICS |
|---|---|---|
| Facio taxonomy ID | US_SIC_1987 | US_NAICS_2022 |
| Leaf code | 4 digits | 6 digits |
| Top level | Division | Sector |
| Typical role | Legacy and industry workflows | Current U.S. statistical classification |
| Relationship | Often one-to-many or many-to-many | Often one-to-many or many-to-many |
SIC and NAICS are related—not interchangeable.
Learn how to classify each taxonomy independently, preserve crosswalk ambiguity, connect insurance context without disguising judgment, and govern human review.
Questions, classified.
01What does the Facio classification and enrichment service do?
It turns a business-activity description into governed SIC and NAICS classifications, then connects the selected segment to insurance risk scores, relevant coverage packages, NAIC/SERFF product candidates, and Lloyd's CR1298 sector candidates.
02Can I find a SIC code from a business description?
Yes. Send the description your applicant, broker, or customer already uses. The API interprets the primary activity and compares it with governed SIC records instead of requiring an exact manual keyword.
03Can the API convert a business category to a SIC code?
Yes, when the category describes what the establishment primarily does. Details such as products, services, and customer type can improve the result.
04Does the API return NAICS as well as SIC?
Yes. Facio returns U.S. SIC 1987 and U.S. NAICS 2022 as independent classifications, including their separate hierarchies and relationship provenance.
05Does the service include Lloyd's industry sectors?
Yes. A connected lookup resolves the selected activity to candidates from the Lloyd's CR1298 industry-sector reference. These are review-required compatibility candidates, not an official direct conversion from SIC or NAICS.
06What are the segment risk scores?
Each SIC segment includes seven versioned 1–10 estimates covering fire, burglary, water, third-party, employers', professional, and product liability. Higher means riskier; the scores are segment guidance, not eligibility, pricing, or underwriting advice.
07Does Facio recommend insurance coverages?
Facio returns core and conditional coverage packages relevant to the classified segment, together with review-required NAIC/SERFF product candidates. They are starting points for workflow and review, not coverage advice or a substitute for a business-specific assessment.
08Is SIC-to-NAICS mapping one-to-one?
Not necessarily. The systems were designed differently, and relationships can be one-to-many or many-to-many. Facio preserves that ambiguity.
09What happens when a description is ambiguous?
The API can return ranked alternatives, lower the confidence band, request more context, or mark the result for human review.
10Does the model invent SIC or NAICS codes?
No. The workflow selects from versioned taxonomy records and validates identifiers before returning them.
11Is the API designed for insurance underwriting?
It is designed to support insurance intake, appetite routing, referral rules, portfolio reporting, and human review. Its enrichment data informs workflows but does not make an underwriting decision.
12Which input languages are supported?
The initial release is designed for English and Hebrew input. Additional languages can be introduced as versioned capabilities after evaluation.
Turn business language into connected insurance context.
Add governed SIC and NAICS classification, Lloyd's sector candidates, segment risk guidance, and relevant coverage context to your workflow.
Tell us about your workflow, expected volume, taxonomies, and insurance reference layers.