3-minute walkthrough

How a Veritas dossiergets built.

Type a company registration number. Five independent sources query in parallel. A deterministic scoring engine produces a verdict. Output: a sourced dossier ready for the MLRO queue.

What runs

Five sources, parallel, sourced.

All five run concurrently. Total wall-clock to verdict is bounded by the slowest source, not the sum.

  1. 01

    Registry sync

    ~5 s

    Companies House (UK), Brønnøysundregistrene (NO), CVR (DK), Äriregister (EE), INPI RNE (FR), GLEIF LEI. Officers, status, incorporation date, registered address, declared beneficial owners.

  2. 02

    Sanctions + PEP

    ~10 s

    EU FSF, OFAC SDN, UN Security Council, UK HMT, Swiss SECO consolidated lists — daily-refreshed, fuzzy-matched with corroboration by DOB / country / identifier. OpenSanctions PEP screen (747k entities) against every declared officer + UBO.

  3. 03

    Adverse media

    ~8 s

    Live news search via Brave, LLM-filtered for subject relevance, ranked by Tier 1 / 2 / 3 source quality. Each hit carries a severity tag and a temporal-decay factor — a fine from 2016 weighs less than a fine from last quarter.

  4. 04

    Director identity

    ~25 s

    Each declared director cross-validated against the corporate leadership page (Playwright-rendered with anti-bot evasion), Brave LinkedIn search with role + nationality disambiguation, and OpenSanctions for PEP overlap. 0–100 score per director with sources cited.

  5. 05

    Web presence

    ~12 s

    Domain age via RDAP / WHOIS, DNS reachability + TLS validity, MX presence, Wayback first-snapshot age, GLEIF LEI status, LinkedIn company-page detection.

Wall-clock end-to-end: typically 60–120 seconds depending on adverse-media depth.
What you get back

One dossier. Audit-defensible.

  • GREEN / AMBER / RED verdict with composite 0–100 score
  • FATF-aligned risk breakdown across 5 categories (AML / operational / reputational / identity / digital)
  • Per-director identity score with tier badge + LinkedIn link where committed
  • Per-officer PEP screening result with source citation
  • Web-presence evidence (domain age, GLEIF, MX, TLS, Wayback, LinkedIn company)
  • Adverse-media hits with relevance score + source-quality tier
  • LLM-drafted compliance commentary in senior-MLRO voice (advisory)
  • Source-cited audit memo (Markdown + branded PDF)
  • Full evidence trail — every signal traceable to its issuing authority
Methodology

Deterministic spine, LLM advisory.

The verdict is rule-based. Same input + same lists = same verdict, every time. Versioned, MLRO-approved scoring weights (v1.2.0). FATF-aligned 5-category typology. RED requires either a hard-override trigger (exact sanctions, dissolved entity) or score ≥ 50 with corroboration from at least 2 non-zero categories. Single-category accumulation tops out at AMBER.

Regulated-entity attenuation. When the counterparty is itself a licensed financial institution (bank, investment firm, payment institution), reputational signals from enforcement findings are attenuated 0.5×. Mirrors how real MLROs already discount routine-supervision noise for incumbents.

LLM commentary is advisory. An LLM-drafted paragraph in senior-MLRO voice sits on top of the verdict — agrees / disagrees, flags context the rules can't see, suggests reviewer focus. Clearly labelled. The deterministic verdict remains the source of truth.

Data is local. Sanctions + PEP datasets are mirrored on disk, refreshed nightly from OpenSanctions. No API roundtrip on screening — fast, free, audit-trail-preserving. The 48-hour staleness gate refuses to trust expired data.

Type a company number.

UK, NO, or DK today. EE + FR live as soon as the keys arrive. A sourced dossier in under two minutes.

Start a screening