Architecture · built for regulated environments

Predictable by default. Intelligent where it counts.

Robust AI for regulated markets isn't a larger model wrapped in guardrails. It's an architecture that separates what must be computed exactly from what genuinely requires judgement — and binds both to a governed knowledge asset, with provenance throughout.

The challenge

Regulated environments don't forgive non-determinism.

A front office, a risk function and a regulator impose requirements that a probabilistic model, left to its own devices, cannot meet. Wrapping a creative core in guardrails inverts the risk — you get the unreliable thing at the centre and a fragile cage around it. The robust thing has to be the default.

Requirement

Reproducibility

The same inputs must produce the same output, every run. A number that drifts between runs is unusable.

Requirement

Provenance

Every output must trace to its source data and its reasoning. "Why did it say that?" needs an answer that holds up.

Requirement

Calibrated confidence

The system must distinguish what it knows from what it suspects — and never assert beyond its evidence.

Requirement

Governance & control

Humans must inspect, correct and constrain it, and the knowledge it relies on must be owned and stable.

The principle

Two kinds of work, two kinds of machinery.

Every task decomposes into computable steps and judgement calls. We refuse to blur them. Computable work runs on Deterministic Cores — exact, repeatable, testable. Genuine judgement runs on supervised agents that orchestrate and decide, calling the cores for anything a function can do. An LLM never performs arithmetic a calculator should. A meta-agent — the Architect — decomposes each task, routes every part to the right machinery, validates the result and supervises throughout.

Determinism by default. Agency by exception. Supervision always.
The picture

Foundation models are the engine — powerful, generic, and increasingly a commodity. Your knowledge is the fuel — except, unlike fuel, it doesn't burn off; it compounds. KAIROS is the brain that runs the engine — holding the whole thing within the deterministic, auditable limits a regulated market demands.

The substrate

The Cognitive Mesh, in detail.

Both layers reason over one governed knowledge architecture — not a vector pile, but a navigable structure with status and provenance on every claim. It is what makes the deterministic and agentic halves cohere, and what makes the asset compound.

Two query modes

Traversal follows the knowledge graph along curated relationships; extraction pulls exact sections on demand. Agents choose the mode the task needs.

Runbooks as compiled paths

A known procedure is a fixed traversal through the Mesh — so the routine executes identically every time. Determinism for the known; agents for the novel.

Epistemic metadata

Every claim carries a status. Agents weight confidence accordingly and cannot assert as fact what the Mesh marks as contested. Hallucination is bounded by design.

EstablishedConventionHypothesisHistoricalContested
Provenance, made concrete

Every output decomposes into a chain you can audit.

Because computable steps are deterministic and judgement is reasoned over a provenanced Mesh, any result reconstructs into an inspectable trace — which data, which tools, which knowledge and its status, which judgement, at what confidence.

"Does this relationship breach its CSA threshold?"trace
DeterministicParsed CSA terms — threshold, MTA, eligible collateral.source · CSA-BR-2021.pdf §3 · doc-store ref 4821
DeterministicComputed net current exposure across 7 live trades.valuation tool v2 · inputs + result recorded
MeshApplied breach definition — market convention.mesh node "csa.threshold-breach" · status: established
AgenticAssessed materiality given counterparty profile and recent activity; confidence calibrated to evidence.reasoning recorded · no assertion beyond mesh status
DeterministicRe-validated arithmetic and output schema before release.validation pass · green
OutputExposure exceeds threshold by $1.4m — material. Full chain attached.
What the design achieves

Provenance, compounding and compliance — by construction.

These are not features layered on top. They fall out of the architecture itself.

01 · Provenance

Auditable by design

Every output is a chain of deterministic steps and Mesh claims with their sources and status. Reproducible where computed, attributable where reasoned. The audit trail is the system's normal output, not a forensic reconstruction after the fact.

02 · Compounding

The asset accretes

Durable learnings settle into the owned Mesh — compiled runbooks, enriched claims, expert corrections — not into opaque model weights. The knowledge asset compounds while the model underneath stays swappable. You upgrade the model and keep the asset.

03 · Compliance

Shaped for the regime

Reproducibility, auditability, calibrated confidence, human control and model-independence — the exact properties a risk and compliance function demands. Because they're structural, they hold as the system grows, rather than degrading at the edges.

The hard part isn't the model

It's the discipline around it.

Most systems put the model at the centre and hope. KAIROS puts determinism at the centre and invokes agency deliberately, under supervision — the difference between a demo and a system you can run in a regulated front office.

Request a technical walkthrough