End-to-End Compliance Platform

From import to audit-ready export. Every step of the compliance process in one place.

Early access. Sanctions lists are subject to change by their issuing authorities.

Flexible Import

Any format. Any structure. Automatic classification.

Upload your screening list in any standard format — or enter names directly. The platform accepts structured data (Excel, CSV, JSON) and unstructured documents (PDF, Word). Each entry is automatically classified as person, organisation, or vessel, and this classification drives the matching logic throughout.

What the import handles

Structured import: Excel sheets and CSV files with automatic column detection. Smart mapping identifies name, date of birth, nationality, and other fields without manual configuration.
Document import: PDFs and Word documents are processed with AI-powered entity extraction. Names are identified in unstructured text and classified automatically.
Direct entry: Names can be entered manually or pasted for ad-hoc screening.
Entity classification: Person, organisation, vessel, or aircraft — determined automatically. Classification affects matching thresholds and scoring logic throughout the entire pipeline.

Structured Review Workflow

Every match reviewed. Every decision documented.

Potential matches don't surface as a raw list — they flow through a structured pipeline. Each result is risk-tiered, routed to the right review stage, and requires an explicit decision with documented rationale. Nothing is silently discarded.

The five-stage pipeline

Screening: Names are matched against all active sources simultaneously. Results above threshold enter the pipeline.
Risk-tiered workbasket: Results are sorted into zones by score. High-confidence matches surface first. Low-risk results can be bulk-cleared with a configurable auto-clear threshold, capped to prevent accidental clearance of true positives.
Validation: Each result is reviewed with full context — match score, source, listed reason, legal basis, biographical data comparison.
Decision: Accept or dismiss, with mandatory rationale. Every decision is timestamped and attributed to the reviewing user.
Export: Completed reviews generate an audit-ready compliance report with one click.

AES-256-GCM Encryption

Field-level encryption. No external calls during screening.

Screening data is encrypted at the field level using AES-256-GCM with HKDF key derivation. Encryption happens on your infrastructure — no data is transmitted to external services during screening. Your counterparty names, match results, and decisions never leave your environment unencrypted.

Encryption details

AES-256-GCM: Authenticated encryption that detects tampering as well as unauthorised access.
HKDF key derivation: Keys are derived per-field using HMAC-based key derivation — no single master key unlocks everything.
At rest and in transit: Screening data is encrypted in the database and over all connections.
No external API calls during screening: The matching pipeline runs entirely on your infrastructure. Counterparty names are never sent to third-party services.
On-premise deployment: The entire platform runs in your environment. Data sovereignty is structural, not policy-based.

Audit-Ready Export

One click. Full documentation. Regulator-ready.

When regulators, auditors, or internal compliance teams request documentation, it is ready immediately. Every screening session produces a complete compliance report — including every match considered, every decision made, every rationale recorded, and the timestamp and user attribution for each action.

Compliance documentation is not an afterthought. It is generated automatically as a by-product of the review workflow — no manual compilation required.

What the export contains

Full decision trail: Every result reviewed, accepted, or dismissed — with rationale and reviewer identity.
Timestamps: Date and time of every action in the workflow, from screening to final decision.
User attribution: Every decision is linked to the reviewing user — audit trail is individual, not aggregate.
Match context: Score, source, match algorithm, listed reason, and legal basis included for each result.
Project-level summary: Overview statistics for the screening session — total screened, matched, cleared, accepted.

Alert-Screen & Autoscreen

Ongoing monitoring. Automatic re-screening. Immediate alerts.

Positive screening decisions automatically enroll entries for ongoing monitoring. Every night, Autoscreen re-checks all enrolled names against freshly updated sanctions lists. New listings, delistings, or changed identifiers trigger an alert immediately.

How ongoing monitoring works

Automatic enrollment: When a screening result is confirmed as a positive match, the entry is automatically enrolled for ongoing monitoring — no manual setup required.
Nightly re-screening: Every night, all enrolled names are re-screened against the latest sanctions data. Changes are detected within 24 hours of a list update.
Alert types: New listings, delistings, changed identifiers, score changes, and new source additions each generate a distinct alert type.
Available to every user: Alert-Screen and Autoscreen are included in all subscription tiers — ongoing monitoring is not a premium add-on.

AI-Powered Match Analysis

Plain-language briefings from official sanctions data. In early access.

For each potential match, AI generates a structured briefing from the official sanctions record: who is listed, why, under which programme, since when, and what restrictions apply. Reviewers get the context they need without manually parsing legal texts.

A chat interface allows follow-up questions against the sanctions data. AI analysis is powered by Anthropic's Claude API — match context is transmitted over an encrypted connection. This feature is optional and can be disabled per project.

What AI analysis covers

Listing summary: Programme, designation date, listed reason in plain language.
Legal basis: Regulation CELEX reference and amendment history where available.
Biographical comparison: Structured comparison of name variants, dates of birth, nationalities, and identifiers between the query and the sanctions record.
Follow-up chat: Reviewers can ask specific questions about the match — the AI answers from the official data, not general knowledge.
Data handling: AI analysis is powered by Anthropic's Claude API. Match context is transmitted via encrypted TLS connection. No data is retained by the AI provider beyond the request. This feature can be disabled per project.

PEP Screening

Politically Exposed Persons from Wikidata and 8 national parliamentary sources.

Sanctions screening and PEP screening address different risk categories but share the same underlying challenge: name matching across transliterations, aliases, and spelling variants. PEP screening uses the same multi-algorithm pipeline, applied to official parliamentary and government databases.

PEP data covers 44,000+ persons from Wikidata, CIA World Leaders, and 8 parliamentary sources (Bundestag, Landtage, EU Parliament, UK Parliament, US Congress, Norwegian Storting, Dutch Tweede Kamer, and Brazilian Câmara). All sources are integrated into the screening index and updated regularly.

Sanctions Screening Built to Be Audited.

Full screening functionality across all official sources, the complete review workflow, and audit-ready exports. A Data Processing Agreement (DPA) can be concluded electronically without delay.