What We
Measure

Not the model's internals. The observable interface between AI systems and the world — the surface you can instrument, model, and act on.

§ 01 · Definition

The Arkheia Surface

The set of all measurable signals that are externally observable when an AI system is invoked — including observable signals, invocation context, output structure, cross-component interactions, and response metadata.

Surface isn't the code itself. It's the observable interface between AI systems and the world — the layer where enterprises can instrument, model, and act. That framing matters because it shifts the conversation from inaccessible model internals to measurable boundary behaviours.

AI System

LLM · Agent Pipeline · RAG System · Tool Chain

Surface Layer

Observable Boundary

tokenstimingcontextstructuremetadatainteractions

Arkheia Engine

Baseline · Detect · Classify · Alert

§ 02 · Feature Space

Separable populations in feature space

Arkheia characterises behaviour across dozens of dimensions simultaneously. The specific features and their combinations constitute our core detection IP. What emerges is a measurable separation between genuine and at-risk populations.

Genuine population

Responses whose multi-dimensional feature profile clusters within the established behavioural baseline for this model family.

Elevated-risk population

Responses whose feature profile deviates measurably from baseline — a statistically distinct cluster that Arkheia surfaces for review.

The separation is detectable without reading the content of any response. Detection occurs at the boundary — the surface.

§ 03 · What This Enables

Behavioural Baselines

Establish what normal looks like for each model, in each context, under each workload. Deviation from baseline is the primary detection signal.

Real-Time Detection

Surface signals are observable during inference, not after. Risk assessments update per-invocation, not per-batch.

Model-Specific Profiles

Each model family has a distinct surface signature. Profiles are built per-model, not applied universally — which is why they work.