Platform

The financial-crime department, in software.

Agents investigate through fixed agentic workflows. A deterministic engine makes the call: every rule versioned, every score reproducible. Your analysts stay in command.

Eight products on one governed flow.

The products · eight, one platform

Eight products. One governed flow.

Each one solves a specific compliance job. All eight run on the same architecture (agents gather the evidence, a deterministic engine makes the call, your analysts command) and draw on the same shared capabilities.

Wallet risk arrives through the blockchain analytics you already trust (Chainalysis, TRM, Elliptic) and enters the same versioned engine as every fiat alert. We don't read the chain. We decide the case.

See the tools that power them

Architecture · one governed flow

Where a model can act, and where it can't.

Two intake rails, banking and virtual assets, feed one governed architecture. Agents investigate, a deterministic engine decides, your analysts command. Two limits are drawn into the picture below: when the rules are already confident the language model is skipped, and a sanctions mandate goes to a named human instead of into a score.

Rail A Banking & fiat AML
Rail B VASP & digital-asset AML
  1. 1

    Data sources

    • KYC
    • Transactions
    • Documents
    • Registries
    • Watchlists
    • Blockchain providers
  2. 2

    Agentic investigation

    • Gather
    • Match
    • Corroborate
    • Verify

    The gate · deterministic rules run first

    Rules confident → language model skipped entirely

    Rules unsure → language model gathers & corroborates, then hands evidence back

  3. 3

    Decision engine

    • Rules
    • Scores
    • Mandates
    • Version control
  4. 4

    Analyst cockpit

    • Clear
    • Refer
    • Escalate
    • STR pack
  5. 5

    Learning loop

    • Precedent
    • Labels
    • Rules
    • Models
Sanctions mandate

An exact watchlist match is never turned into a score. It skips the model and the score — never the evidence: deterministic gathering still files the match record and its receipts — and is held for mandatory review by a named person, above the ranked queue.

no model · no score · evidence still filed

How the call gets made.

Investigate. Decide. Command. In that order, every time.

Agents investigate

Seven agentic specialists gather the evidence: names, graphs, registries, documents, media, precedent. Language models do the reading (resolving name variants, extracting scanned documents, sweeping adverse media) and every finding is tied to the record behind it. What a model can't corroborate is flagged, never asserted.

The engine decides

A deterministic engine fuses every signal under versioned weights. Same inputs, same score, every time. When the rules are confident, the model is never called at all.

Analysts command

Every disposition takes a reason code and a countersignature the schema physically requires. Confirmed suspicion produces a verified STR narrative and a goAML-aligned pack for the MLRO to file. The score is a recommendation; the decision is your analyst's.

See it on your own alerts.

Bring up to 5,000 historical alerts. Two weeks later you're reading your own numbers, not our brochure.