Agent Economy Runtime Audit Pack

Note (dated 2026-08-04): a chain composes independent computations performed in an analytical order. No step's output is carried into the next step by the execution model; each step computes from its own declared inputs. This is true of every chain on this site, including chains whose per-step copy below reads as a data handoff.

W-G convergence terminal. Merkle integrity over the runtime decision set (cry-04) -> one Merkle-root audit receipt (cry-05) -> platform/regulator-framed cover memo (ptg-01). Other Wave-14 chains can feed in.

OpenChainGraph · 3 Steps prompt template Hash-Anchored §4 chain_depth:3 Client-Side · Zero PII

Chain Stages · 3 Steps

1 ROOT · D0 node

Merkle Batch Verifier cry-04-merkle-batch-verifier

batch integrity (H1) feeds the aggregator

MCP Call · verify_merkle_batch

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "verify_merkle_batch",
    "arguments": {}
  },
  "id": 1
}

↓

2 D2 node

Agent-Action Audit-Trail Aggregator cry-05-agent-action-audit-trail-aggregator

Merkle-root receipt (H2) feeds the memo generator

MCP Call · aggregate_execution_receipts

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "aggregate_execution_receipts",
    "arguments": {}
  },
  "id": 1
}

↓

3 TERMINAL · D3 node

AP2 Prompt Template Generator ptg-01-ap2-prompt-template-generator

Exports composite audit pack with Merkle-root execution_hash (H3), final stage

MCP Call · compose_ap2_prompt

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "compose_ap2_prompt",
    "arguments": {}
  },
  "id": 1
}

Question: Quarter-end is here and we must evidence what our agents did. Do the executed receipts actually verify against the pack root? Run the AINumbers MCP tool `run_chain` with {"chain":"agent-economy-audit-pack"} and read `cry-05-agent-action-audit-trail-aggregator.all_proofs_verified`. Re-run with `inputs` for `cry-05-agent-action-audit-trail-aggregator`, reusing the values that result echoed, with `artifacts` changed so one executed receipt joins the audit pack. Compare the same field. Verify: call `verify_execution_hash` (https://mcp.ainumbers.co/mcp) with `claimed_hash` set to `composite_execution_hash` and the full `composite_artifact`. Ledger, for a human re-check: https://ledger.ainumbers.co/ PII rule: send synthetic or anonymised inputs only. The MCP server runs these kernels and logs no payloads. Chain page: https://ainumbers.co/chaingraph/chains/agent-economy-audit-pack.html

Agent Economy Runtime Audit Pack

Ask your agent