Every Saolix product is designed around one line. Above it, AI is allowed to help. Below it, only rules decide. We call it the determinism boundary, and it matters more than any model we could put above it.

The idea is simple to say and surprisingly hard to hold. Language models are useful in compliance work: they read messy evidence quickly, explain a match in plain English and help an analyst decide where to look first. They are also probabilistic. Ask the same question twice and the answer can change. A screening decision that a bank must defend to an examiner cannot work like that.

So we split the work. This piece describes how that split is implemented in Saolix Eagle, our AML and sanctions screening engine.

Below the line: rules decide

When Eagle screens a name, the verdict comes from a deterministic pipeline. The name is normalised and transliterated, then compared against the sanctions lists with a layered combination of industry-standard matching techniques. The combined score is mapped by configured thresholds (changed only with a second person's approval) to one of three verdicts:

  • PASS: no meaningful match
  • REVIEW: a possible match that a person must look at
  • FAIL: a strong match, but only when an identifier such as a date of birth or document number was supplied with the screening. Without one, even a strong name match is capped at REVIEW and goes to a person.

The rules version in force is recorded with every screening. The same input under the same rules gives the same verdict, every time.

The model can suggest where to look. It cannot change what the rules concluded.

Above the line: AI assists

Eagle has two kinds of AI help. In the analyst screen, a triage copilot explains each alert in plain language, without a language model in the loop. Separately, Raia, an optional AI agent in Eagle, runs on a language model hosted inside the customer's environment. Eagle can also show an AI-written summary in the case view. Nothing is sent to an outside AI service.

Raia labels each alert to help analysts decide where to look first. If the AI is unavailable, the alert goes to a person: when in doubt, Eagle errs towards human judgement.

The guard on the line

The boundary is not a policy document. It is code. Before any AI label is used, a guard checks it against the rule engine's result. Whenever the two disagree, the rules win: the label is overridden to review, and the override is recorded.

And nothing downstream uses the AI label to close a case. Eagle keeps it as an advisory note only, and nothing in the product acts on it. There is no path by which Raia or the copilot resolves an alert on its own.

A screening flows through the rule engine to a verdict. An AI label passes through a guard that overrides it to review whenever it disagrees with the rules. The label is stored only as an advisory note. THE GUARD ON THE LINE AI labeladvisory Guardthe rules win Advisory notenever decides Rule engine verdictPASS · REVIEW · FAIL Case outcomedecided by people DETERMINISM BOUNDARY
An AI label can only ever be advisory. When it disagrees with the rules, the guard sides with the rules.

The AI can always be switched off

AI assistance has its own switch, and it is built not to affect decisions: with AI assistance off, every screening still reaches exactly the same verdict. The analyst just loses the help. And whatever the AI says is kept only as an advisory note alongside the case, never as part of the decision.

Why this is the right trade

It would be easy to let the model do more. It is often right. But "often right" is not a standard a regulator accepts, and it is not one a customer should accept either. Keeping the model above the line means it can be upgraded, replaced or switched off without changing a single decision. It means an examiner can ask why an alert fired and receive an answer that does not depend on a model's mood that day.

That is the determinism boundary. The same line runs through the other modules of Saolix Eagle, the Compliance Hub: eKYC, Fraud and Transaction Security, and you can see it in action in the Eagle Simulator.