Platform
One call, before the action. Either it verifies, or it refuses.
Hetu is a verification layer your agent calls at the moment it wants to claim something or do something. It computes the answer deterministically where it can, labels its own confidence, and returns a record an auditor will accept.
What gets verified
Three things, in this order: the figure, the cause, and the right to act.
The figure. Every number in an agent's output comes from a deterministic rule engine or a fitted causal model, never from the language model. If a figure cannot be computed from a source the system can name, it is not returned.
The cause. Attribution is a statistical result with intervals and a residual, not a sentence. It carries a confidence label computed from explained variance and interval overlap, and the narration is bound to that label.
The right to act. A verified conclusion is not automatically an authorised action. The autonomy envelope decides whether this decision type, at this confidence, at this magnitude, can execute without a named human approver.
Where it sits
Between the agent's reasoning and its tool call.
Structured in
01 · Question
Your agent sends a decision request: the entity, the window, the metric, the action it intends. Not a prompt — a payload against a schema.
Cascade runs
02 · Verify
Rules first, causal model second, constrained hypothesis generation last. Each tier has explicit stopping criteria and escalates rather than guesses.
Guard checks
03 · Label
Temporal ordering, magnitude consistency, hard gates, sample floor, label binding. Any failure refuses the conclusion instead of downgrading it.
Act, defer or refuse
04 · Gate
The response says which of the three it is, why, and what would change the answer. Everything is written to the decision log either way.
The intercept
One call, three ways out.
The agent asks before it acts. What comes back is a disposition, not a suggestion — and the record is written whichever way it goes.
Act
Deterministic or statistically attributed, every guard passed, decision type inside the proven envelope.
Approve
Verified, but above the magnitude ceiling or outside the envelope. It queues with the evidence attached.
Refused
A check failed. The intended action is held, the failed check is named, and the falsification test comes back with it.
Integration
One endpoint, model-agnostic, no data leaves your perimeter.
The narration model is swappable and the reasoning does not depend on it, because it never did any reasoning. A model upgrade improves the sentences and changes none of the maths.
The shape of it
A payload in, a labelled verdict out.
Nothing in the response is prose the model invented. Every field traces to a computation or a check that ran.
In
The entity, the window, the trigger metric and the action the agent intends to take, against a schema.
Out
A disposition, a confidence label, the attribution with intervals, the guard results and a link to the record.
In detail
The four parts, documented.
Design partners
Bring the decision you don't currently let an agent make.
We map your constraints, seed the graph with your experts, and show you the first refusal.