Outcomes use your displayed policy and session history; editing either can change the verdict. Presets marked 2026 incident are drawn from documented agent payment failures. The rest are the everyday cases the gate sees.
Editable. Every change rebuilds the policy set that the engine evaluates against. Amounts are in whole US dollars for readability; the engine works in integer minor units under the hood.
Propose a payment
What the agent wants to do
Fill in a spend intent and send it through the gate.
Verdict
No decision yet
Send a proposal or pick a scenario. The engine returns allow, require approval, or deny, with a stable reason code and a decision fingerprint.
Session decision ledger
Every decision, with its fingerprint
A demonstration of the tamper-evident-record idea. In the hosted product this is a persisted, hash-chained ledger. Here it lives in memory for this session only.
Nothing yet.
What you are looking at
How the gate decides
The engine checks amount, counterparty, agent and time against your policies.
Hosted Axiru adds live approvals and a persisted evidence ledger. See the open source page for details.
Next step
Take your controls live
Start in shadow mode, then set up live enforcement with human approval.
Start with a free replay. Turn on live enforcement later.