Transparency

A public trust surface for how Neura Relay returns governed results

The public contract is simple: outputs are reviewed before downstream use and returned with a decision state, reviewed output, rationale, confidence range, and trace framing.

Current public contract
What is public

Playground, developers page, resolve response contract, decision states, confidence range, and trace framing.

What remains internal

Deeper arbitration logic, calibration strategy, and the full production hardening path.

Decision states

Three states drive the public proof surface

The current Playground, homepage demo, and developer examples are all built around the same three states.

Needs review

The output should not move downstream yet because the system found enough uncertainty, missing conditions, or operational risk that a human should inspect it first.

Revised

The original output was directionally useful, but not safe enough to use as-is. Neura Relay returns a reviewed version that adds the missing conditions before anything moves forward.

Ready

The output held up under review and can move forward without material change.

Inspectable result

What the public trust model actually exposes

Reviewed output

The governed result separates the reviewed output from the original so downstream systems can act on the reviewed version instead of the raw one.

Confidence range

Confidence is shown as a range to reinforce that review is a bounded judgment after challenge, not a magic stamp.

Trace framing

The public trace shows the review path in a compact sequence that is easier to inspect than a single raw answer.

Protocol framing

The current public surface is grounded in tasks, runs, trace rows, and protocol versioning rather than isolated UI copy.

Current governed result shape
{
  "decision": "revised",
  "reviewed_output": "Reply that we are open to the offer, but need final confirmation on price and timing before accepting",
  "rationale": "The original output moves too quickly toward commitment.",
  "resolution_score": 72,
  "confidence": {
    "low": 48,
    "high": 96
  },
  "trace": [
    "Inspect output",
    "Challenge assumptions",
    "Audit reasoning",
    "Produce reviewed output"
  ]
}
Boundary

This page explains the public model, not the internal system

The goal is clarity. This page documents the trust signals the current public site can honestly support today without simulating internal depth.