Altien^AI/Ratio
Altien Ratio™ · The symbolic reasoning engine inside Altien^AI
For supported areas of law, Ratio assesses stated circumstances against maintained automated legal rules — and shows the authority, the satisfied requirements and the open questions. Professionals review reasoning, not a confidence score.
First, an honest word
A language model does not think. It has read more of human thought than any person ever will, and it is remarkably good at producing the answer that looks right — the argument shaped like the arguments experts make. That is fluency, not reasoning. Most of the time it is enough. Sometimes it isn’t, and the model cannot tell you which time this is.
Checking it yourself runs into an awkward paradox. If you already know the answer, you didn’t need the machine. If you don’t, you are now researching the very question you asked it — verifying fluent work in a field where you can’t see the joins.
The numbers are genuinely impressive. Depending on whose benchmark you read, today’s best models are somewhere between 80% and 95% correct, somewhere between 80% and 95% of the time. Now hold that against the standard you apply to people. You would eventually part company with an adviser who was right eight times out of ten by luck. The model offers similar odds, shows you no working — and is rather harder to dismiss.
This is not hypothetical
The famous failures were invented cases — Mata v Avianca, the headlines, the sanctions. Any competent legal AI now checks that a cited case exists. The failure that survives that check is quieter: a real authority, cited for something it never said.
In Coomer v Lindell, the court found some thirty defective citations in a single brief: misquotations, misstated holdings and real cases cited for propositions they do not stand for. A handful were invented; most existed. Existence was never the problem. Counsel and co-counsel were fined $3,000 each.
The sanctions order ↗Ten months later the same counsel was sanctioned again — $5,000 this time — for filings that, in the court’s words, “misrepresent what courts have said”. He told the court he had cite-checked the brief himself. The citations were real. The propositions were not. An adviser on a second warning; a tool that does not take warnings.
The second order ↗In Gauthier v Goodyear, a summary-judgment response attributed fabricated quotations to six real cases, alongside two invented ones. Every one of the six would have sailed through a does-this-case-exist check. Counsel was sanctioned and ordered onto a course about generative AI in legal practice.
The order ↗A citation checker verifies that the case exists. Nothing in that pipeline verifies the argument. Whether an authority actually supports the proposition it is cited for is a question of reasoning — and that is the gap Altien Ratio closes for supported areas of law. A Ratio conclusion is not written first and checked afterwards. It can only exist when the requirements of an approved, versioned rule are satisfied by the stated facts, with the provisions linked. The connection between proposition and authority is not asserted by a model; it is the structure of the answer itself.
And this is no longer only about reputation. In London, the Divisional Court has already referred lawyers to their regulators over unverified authority, and a public database logs new court decisions on the failure roughly five times a day. It is your licence.
∴ Compliance, one enquiry at a time — verifiable by design. Checking stops being research and becomes review.
Why “Ratio”
Every lawyer learned the word in their first week: the ratio is the reasoning a decision stands on. That is exactly what this engine produces — not just an answer, but the rule applied, the facts that satisfied it and the questions still open.
Under the hood this is what researchers call neuro-symbolic AI: language models for the everyday work, symbolic legal rules for the assessment. We prefer the name lawyers already know.
Altien Ratio · Illustrative assessment
RatioDoes the exception permit the proposed action on these facts?
The current facts support two requirements. A third turns on the purpose and timing of the action.
What the reviewer receives
What follows from the circumstances provided in a supported domain.
Relevant provisions remain available for legal review.
Material unknowns and independent requirements are made visible.
The oldest algorithm in law
Lawyers have run this reasoning since Rome. Ratio runs it against maintained rule sets — each requirement tested against the stated circumstances, each conclusion traceable to its rule and its facts.
An approved, versioned automated rule set for the supported domain.
The circumstances you state — and the ones Ratio asks for because they matter.
What follows — or a plain statement that it cannot yet be concluded.
The experience
The additional assurance appears in the result. The user does not need to learn a rules language or choose an internal reasoning system.
Pose a scenario-based question in ordinary legal language.
Add only the circumstances that could materially affect the result.
Examine the assessment, authority and unresolved issues.
Apply professional judgment and retain the review record.
Where it fits
Ratio assessments are available for supported regulatory domains with approved automated rule sets. They strengthen suitable scenario-based questions while keeping professional legal judgment in control.
Talk to us about the legislation, decision patterns and review standard your organisation needs to support.