3 Primitives Logo

Upstream Safety System (USS™)

Upstream Safety System™ | Live Demo | 3primitives.io

We built this before we knew
what we had found.

In late 2025, we were trying to solve a specific problem: how do you make an automated decision about a person legitimate at the moment it happens. Every other approach intervenes after the fact. The USS intervenes before. Because of that, every decision it permits is also reconstructible, auditable, and defensible. Not as a feature bolted on. As a structural consequence of getting the timing right.

You already know what Ghost Authority feels like.

A decision was made about you. You do not know who made it, what they were authorised to decide, or whether anyone was accountable for the outcome. The system acted as if it had authority when no human ever declared it.

That is Ghost Authority. It remains structurally identical whether it happens in a hospital, a welfare office, a bank, a hiring process, or a care home. The domain changes. The structure does not.

The USS exists to make Ghost Authority structurally impossible. Not as a policy or a guideline. As a gate that either opens or stays closed.

Select your position and a domain below. The gate runs on two versions of the same decision: one with declared authority and one without. Watch what the mathematics does to a real decision.

Who this is for
The person affected
"A decision was made about me and I have no idea who made it or why."
The regulator
"I cannot audit this. There is no declared authority on record. This is ungovernable."
The institution
"We deployed that system. We have no documentation of who authorised it to decide."
The lawyer
"There is no declared authority, no δ, no named human. You have no defence in discovery."
I make decisions about people.
Decisions are made about me.
Select a domain
Subject
System acting as authority
Human who should declare authority
Ghost: Undeclared
GAMMA — gate blocked. No declared authority found. The action cannot proceed.
g          false
L_valid    false
state      GAMMA
gate_hash  null
error      403-GA
Declared: Authority Stated
ALPHA — gate passed. Authority declared, scope valid. The action may proceed.
g          true
L_valid    true
state      ALPHA
gate_hash  [SHA-256]
replay     FIRST_SEEN
What this means

What the gate just decided

What declared authority changes

Why this matters to your institution

How the USS™ works in practice

The USS does not sit across every decision.

Each organisation defines what counts as high risk for their context. That definition is theirs. A hospital decides which clinical actions require declared authority. A lender decides which credit decisions fall within scope. Once defined, that small category of decisions moves through the gate.

Some of those decisions are handled at the design stage, built into the system before it ever sees a live case. Others run through the API at the moment of decision. Either way, the gate applies the same rule: declared human authority must exist before the action proceeds.

In the rare case where authority cannot be confirmed, the gate stays closed. The action waits. This is not a bottleneck. It is the system doing exactly what it is supposed to do. In most domains, a decision that cannot be authorised immediately is a decision that should wait. The gate holds it there safely until someone with authority can sign off.

What is running underneath

USS™ v2.4 is a deterministic, rule-based governance engine. Three detection layers. Four structural violation rules. Eleven automated decision categories derived from a mathematical closure across two domains. Seventy-five tests passing across eight test files. Every invariant enforced directly in code.

Severity is separated from impact. Decision is separated from measurement. Authority is separated from outcome. No machine learning in the decision path. Classification informs. Only the gate decides. No probability thresholds. No blended scores. No scalar collapse. No hidden weighting.

Existing governance systems describe what should happen. The USS™ enforces what structurally can happen. It is not a policy layer bolted onto an existing system. It is the layer that determines whether the system has permission to act at all.

The proof runs.

Engage with us

We welcome inquiries into the USS™ from institutions, regulators, and implementation partners.

[email protected]