Products

Compliance engines. One discipline.

Agentic AI on top, deterministic rules underneath. On-prem, quantized LLMs re-rank and explain, RAG keeps every reason grounded, and GenAI drafts the report. The verdict stays rule-driven, auditable and reproducible.

What we build

Four products.

Eagle · AML & sanctions screening

Saolix Eagle

Financial-crime screening that returns verdicts, not guesses.

A deterministic match chain produces byte-identical, reproducible results, with a tamper-evident audit trail and a regulator-replay endpoint that reconstructs any decision exactly. On top sits an agentic AI triage copilot: an on-prem, quantized LLM that re-ranks the alert queue and drafts RAG-grounded, plain-language explanations, with GenAI case reporting. It advises; the rules decide. Runs air-gapped, on your own infrastructure.

  • Agentic triage copilot: on-prem LLM, advises, never decides
  • RAG-grounded reasons and GenAI case reports
  • Reproducible verdict: same input, same output
  • SHA-256 audit row and regulator-replay endpoint
Ask about Saolix Eagle →
Known2Me (K2M) · agentic eKYC & identity

Saolix K2M

Verify the human, not the image of a document.

Document checks alone are finished: AI forges a perfect passport in seconds. Known2Me (K2M) runs agentic eKYC and LLM- and RAG-based profile scoring, real-time and batch, leaning on the signals AI still cannot fake: liveness, behaviour over time, device and network provenance, and claims tied to a real issuing authority rather than a scanned file. GenAI drafts the report.

  • Agentic eKYC and profile scoring, real-time and batch
  • LLM and RAG based, with liveness and behaviour signals
  • Claims-based and issuer-anchored, with GenAI reporting
Ask about Saolix K2M →
F2X · fraud & risk management

Saolix F2X

See the pattern before it becomes a loss.

Saolix F2X detects emerging fraud and operational risk across customers, accounts, transactions, devices and digital journeys. Behavioural, velocity, network and anomaly signals are continuously evaluated in real time and batch. An agentic investigation copilot connects related activity, prioritizes alerts and drafts RAG-grounded explanations for the analyst. It surfaces the risk; governed rules and policies determine the action. Every score, recommendation and outcome remains traceable and auditable.

  • Real-time and batch fraud monitoring across transactions and accounts
  • Behavioural, device, velocity, network and anomaly signals
  • Agentic investigation copilot with RAG-grounded risk explanations
  • Governed risk actions, traceable decisions and audit history
Ask about Saolix F2X →
Shield · cyber security

Saolix Shield

Turn security signals into governed, auditable action.

Saolix Shield brings together identity, network, endpoint, application and cloud-security signals to expose threats that isolated controls can miss. An agentic security copilot correlates events, prioritizes incidents, explains the attack path and drafts response guidance using organization-approved knowledge. AI assists the security team; deterministic policies and authorized workflows control every response. Designed for customer-controlled environments where security evidence, operational visibility and data sovereignty matter.

  • Unified threat visibility across identity, network, endpoint and cloud
  • Event correlation, attack-path context and incident prioritization
  • Agentic security copilot with grounded investigation and response guidance
  • Policy-controlled workflows and a complete operational audit trail
Ask about Saolix Shield →
How it works

One pipeline. A hard line through the middle.

First, AI reads, resolves and ranks: fast and probabilistic. Then the verdict, the decision and the audit trail are rule-driven and reproducible. The only thing that crosses the line is a recommendation; the decision is always made on the deterministic side.

01 · AI assists

Ingest

Resolve and normalize entities.

02 · AI assists

Screen

Sanctions, PEP and adverse media.

03 · AI assists

AI triage

LLM re-rank and RAG-grounded reasons.

04 · Rules decide

Rule engine

Pinned ruleset, reproducible.

05 · Rules decide

Verdict

Clear or escalate.

06 · Rules decide

Audit

SHA-256 audit row and regulator replay.

See it in practice

What a verdict actually looks like.

Every screening leaves an explainable record. The AI’s probabilistic candidates and plain-language reasons sit on one side; the deterministic verdict and pinned ruleset on the other; the whole thing sealed with a hash you can replay in front of a regulator, byte for byte.

See it against your own cases.

Tell us what you screen and where it runs. We will show how the products fit your infrastructure and jurisdiction.