How Aethis works

Documentation Index

Fetch the complete documentation index at: https://docs.aethis.ai/llms.txt

Use this file to discover all available pages before exploring further.

​

The idea

A language model reads your source material — potentially multiple documents covering different aspects of the same legislation — and generates rules organized into logical sections. Those rules compile to formal constraint logic. After that, every decision is pure evaluation — deterministic, fast, and traceable to the source clause that produced it.

​

What the engine delivers at runtime

Once a ruleset is published, the engine provides three capabilities — all without a language model in the path: Eligibility decisions. Pass input data, get eligible, not_eligible, or undetermined in under 5ms. Deterministic: same inputs, same answer, every time. At scale, thousands of evaluations per second. Explanations with source citations. Every decision traces to the specific criteria and source clauses that produced it. The engine returns each criterion with a human-readable rule description and the regulation or policy section it was compiled from — not a probability distribution, but a complete audit trail. Guided eligibility flow. Instead of requiring all fields upfront, the engine can guide a user through questions one at a time, identifying the minimum set needed to reach a decision. It evaluates all eligibility paths simultaneously — not a fixed decision tree — so it finds the shortest route through complex, interacting requirements. If a single field is disqualifying (species is Vogon), the engine stops immediately without asking further questions. If multiple routes to eligibility exist, it navigates the cheapest path first. Gap detection. When no rule covers a particular combination of inputs, the engine returns undetermined rather than guessing. This surfaces missing coverage during authoring — rule authors can see exactly which input combinations fall outside the compiled rules.

​

Why not just use an LLM at decision time?

Language models are good at interpreting rules. They are not reliable at executing them consistently. The failure mode is silent: the model reads the policy, reasons through it, and returns a confident, well-structured answer — that is sometimes wrong, with no way to know when. The same question asked twice can produce different answers. The same question asked differently almost certainly will. In regulated domains — insurance underwriting, benefits entitlement, lending, compliance — this is not acceptable for three reasons:

1. Determinism: the same inputs must produce the same decision every time. An applicant who qualifies on Monday must qualify on Friday.
2. Auditability: every decision must trace to a specific source clause. Not eligible because field X does not satisfy condition Y in section Z. A probability distribution over tokens is not an audit trail.
3. Regulatory defensibility: in supervised sectors, AI decision systems must be explainable and reproducible. A stochastic model cannot meet this bar.

Aethis uses language models where they’re the right tool — reading legislation and generating structured rules under test supervision. At decision time, no model is involved. Aethis also differs from decision-tree approaches. A decision tree follows a single fixed branching path. The Aethis engine evaluates all eligibility routes simultaneously, finding the shortest path to a determination across interacting requirements. The compiled rules are not a tree — they are constraint logic that the engine solves as a whole.

​

Do you need multi-section authoring?

​

The three-phase authoring model

​

Who drives what

There is no required division of labour — a developer can author rules end-to-end without any domain specialist involved. In regulated contexts, the person who understands the legislation best will typically:

• Provide or verify the source documents
• Write test cases with expected outcomes
• Review guidance hints for accuracy before the next generation run

Everything else — driving the API, iterating on generation, publishing — is mechanical. A coding agent handles it without oversight. The platform enforces deterministic, auditable decisions at runtime. When a case falls outside the compiled rules, it returns undetermined and flags for human review rather than guessing.

​

Next