Morifar Decision Instrument
SYSTEM CARD / SC-001
PRINT-READY DOCUMENTMorifar Decision Instrument
A transparent description of what the public demonstration does, what it cannot do, and how its claims should be interpreted.
1.2 · Public demonstration and governed-AI gateway
Explain how business intent can be mapped to evidence, risk and accountable authority.
Real risk classification, transaction approval, compliance advice or automated operational action.
Free-form text entered by the visitor. Do not enter personal, confidential, regulated or client information.
The default experience uses deterministic local mapping. Governed AI activates only when a private API key and explicitly verified model are both configured; the interface visibly identifies AI REASONING mode.
Same-origin requests, JSON-only inputs, a 500-character instruction boundary, request-size control, per-client rate limiting, a 20-second safe timeout and strict server-side output validation.
The model must return the published decision-control-map/1.1 schema. Invalid, incomplete or out-of-range responses are rejected rather than presented to the visitor.
The application does not persist submissions. AI requests are sent with model storage disabled; infrastructure providers may still process ordinary security and request metadata.
Illustrative domain, evidence checklist, provisional risk signal, authority route and trace stages.
The visitor initiates every trace. No external system action is available.
Simplified semantics, non-exhaustive policy logic, no jurisdictional rules and no validated risk calibration.
No authentication, database, client connector, upload or external tool permission. Server credentials are never returned to the browser.
Morifar AI · Public experience team
12 July 2026