Live Governed Proof

live-governed-proof is a pack of live proof scripts for real model-backed governed execution. It is the example set to read when you want evidence that AgentXchain is governing actual model output instead of only mocks.

What It Is

• Category: live proof example
• Surface: runner-interface, api_proxy, and MCP proof scripts
• Source: examples/live-governed-proof

Workflow Or Proof Shape

This directory currently contains:

• run-live-turn.mjs for one real api_proxy governed turn
• run-multi-provider-proof.mjs for OpenAI -> Google -> Anthropic governed flow
• run-proposed-authority-proof.mjs for proposal-authority proof
• run-escalation-recovery-proof.mjs for blocked-state recovery proof
• run-mcp-real-model-proof.mjs for real-model MCP proof

How AgentXchain Governs This Example

AgentXchain governs these proofs by:

• writing real dispatch bundles
• validating real turn-result JSON
• enforcing gate progression and completion rules
• recording governed artifacts even when the model is live

This is proof infrastructure, not a sample product.

Run It

node examples/live-governed-proof/run-live-turn.mjs --json
node examples/live-governed-proof/run-multi-provider-proof.mjs --json
node examples/live-governed-proof/run-proposed-authority-proof.mjs --json
node examples/live-governed-proof/run-escalation-recovery-proof.mjs --json
node examples/live-governed-proof/run-mcp-real-model-proof.mjs --json

Credential requirements depend on the script, including ANTHROPIC_API_KEY, OPENAI_API_KEY, and GOOGLE_API_KEY.

Key Takeaways

• This is the clearest live-proof surface in the repo.
• It proves governed execution against real providers, not just static fixtures.
• Use it to validate runtime truth before making product claims.