Why it matters
A match result is not enough.
Regulators and auditors ask what was screened, when it was screened, which list version was active, and why a decision was made. Verifex preserves all of this context automatically.
Confidence scores
Every match includes a structured confidence score (0–100) with documented rationale, so reviewers can inspect — not just trust — the result.
Source context
Results include the exact source list, version identifier, and ingestion timestamp. You can prove which data state was used at screening time.
Point-in-time evidence
Each screening produces an evidence capsule with query input, list versions, algorithm version, and audit ID. Retention is plan-based.
Product flow
From raw name to reviewable decision.
Input
Name, country, entity type, DOB
Normalize
Transliteration, tokenization, deduplication
Screen
Multi-algorithm matching across configured sources
Resolve
Entity disambiguation and alias consolidation
Adjudicate
Confidence scoring with structured rationale
Evidence
Point-in-time audit capsule with list versions
Capabilities
What the API delivers.
Global source coverage
OFAC, UN, EU, UK, and other configured sanctions, PEP, watchlist, and debarment sources. Coverage depends on the active plan and environment.
Multi-script matching
Fuzzy, phonetic, and transliteration matching across Arabic, Cyrillic, Chinese, Greek, and other writing systems.
Entity resolution
Consolidates aliases and transliterations into a single canonical profile, reducing duplicate alerts across sources.
Match confidence
Structured confidence scores (0–100) with documented penalty chains and adjudication rationale for reviewer inspection.
Adjudication support
LLM-assisted entity resolution with documented rationale. Results include confidence scores and reasoning chains for audit review.
Audit trail
Every screen logged with millisecond timestamps, exact list versions, match evidence, and reviewer decisions.
Fast latency
p50 45ms, p95 202ms, p99 276ms on the latest benchmark. Batch up to 1,000 entities per call.
Monitoring & webhooks
Add entities to a watchlist and receive near real-time webhook alerts when their risk status changes due to list updates.
Evidence capsule
Every decision leaves proof.
Each API response includes an evidence capsule that captures the exact state of the screening at the moment it ran. Months later, you can reconstruct what was checked, what version was active, and what the system recommended.
- Query input and normalized name
- Screened_at timestamp with millisecond precision
- Exact source list and version identifier
- Match score and structured recommendation
- Audit ID for cross-reference
{
"query": {
"name": "Rosneft",
"type": "company",
"country": "RU"
},
"screened_at": "2026-05-08T09:14:00.000Z",
"source": "OFAC_SDN",
"match_score": 98.7,
"recommendation": "REVIEW",
"list_version": "v2026.05.08.0600",
"matching_engine_version": "v3.0.0",
"audit_id": "vfx_a_7f3a9d2e..."
}Published benchmark
Measured on our published benchmark.
We publish a transparent benchmark test set covering true positives, false positives, transliterations, aliases, and false positive cases. No sales call required.
500-case benchmark: 99.68% F1, 99.36% recall, 100% precision, verified May 17, 2026.. Self-administered benchmark. Results will vary on different datasets.
Developer experience
Official SDKs and REST API. Ready to integrate.
Integrate in minutes with a single POST request. Batch screening, webhook subscriptions, and evidence retrieval all follow the same REST pattern.
curl -X POST https://api.verifex.dev/v1/screen \
-H "Authorization: Bearer vfx_..." \
-H "Content-Type: application/json" \
-d '{
"name": "Rosneft",
"type": "company",
"country": "RU"
}'{
"matches": [...],
"total_matches": 3,
"risk_level": "HIGH",
"screened_at": "2026-05-08T09:14:00.000Z",
"request_id": "vfx_req_...",
"lists_checked": ["OFAC_SDN", "UN"]
}Related products