OpenChainGraph Suite · CONTRACT A3

CASS 15 Safeguarding 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.
Reading mode (RUNBOOK): Read these steps in this order. The method classification records whether each declared funds stream's asserted safeguarding method is coherent on the supplied facts, the reconciliation check compares the safeguarding requirement with the resource components for the same as-of date, and the evidence pack itemises the auditor's evidence elements with their supporting figures. Each step is supplied its own inputs; nothing is threaded between them.

Three-step safeguarding audit pack for a UK payment or e-money firm under CASS 15. Step 1 classifies each declared funds stream's safeguarding method and records whether the asserted method is coherent on the supplied facts (art-500). Step 2 reconciles the safeguarding requirement against the resource components for the same as-of date, returning a covered, tolerance or shortfall verdict with the gap in minor units (art-499). Step 3 assembles the auditor's evidence pack over the classification and the reconciliation result, itemising each evidence element with its supporting figures (art-501). Each step computes from its own declared inputs; the order is analytical, not a statutory sequence.

OpenChainGraph · 3 Steps compliance mandate Hash-Anchored §4 chain_depth:3 Client-Side · Zero PII
Chain Topology (linear): CASS 15 Safeguarding Method Classifier → CASS 15 Safeguarding Reconciliation Check → CASS 15 Safeguarding Audit Evidence Pack
§4 Execution Hash · Chain Definition Anchor
execution_hash:computing…
Chain Stages · 3 Steps
1 ROOT node
CASS 15 Safeguarding Method Classifier art-500-classify-safeguarding-method
Classifies each declared funds stream's safeguarding method and records whether the asserted method is coherent on the supplied facts, returning a per-stream classification with an overall coherence verdict. Stage 1 of 3. Step 2 then reconciles the safeguarding requirement against the resource components for the same as-of date.
MCP Call · classify_safeguarding_method
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "classify_safeguarding_method",
    "arguments": {}
  },
  "id": 1
}
↓
2 D2 node
CASS 15 Safeguarding Reconciliation Check art-499-check-safeguarding-reconciliation
Reconciles the safeguarding requirement against the resource components for the declared as-of date, returning a covered, tolerance or shortfall verdict with the residual gap in minor units. Stage 2 of 3. Step 3 then assembles the auditor's evidence pack over that reconciliation.
MCP Call · check_safeguarding_reconciliation
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "check_safeguarding_reconciliation",
    "arguments": {}
  },
  "id": 1
}
↓
3 TERMINAL · D3 node
CASS 15 Safeguarding Audit Evidence Pack art-501-build-safeguarding-audit-evidence
Assembles the auditor's evidence pack over the declared classification and reconciliation inputs, itemising each evidence element with its supporting figures and overall pack status. Final stage.
MCP Call · build_safeguarding_audit_evidence
{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "build_safeguarding_audit_evidence",
    "arguments": {}
  },
  "id": 1
}
Export Artifacts
Download the §4 chain definition artifact (hash-anchored composite JSON) or the §13.11 W3C Verifiable Credentials view. Both derive from the chain definition; no new hash is minted. Available after hash computation.

Ask your agent

Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this whole workflow on the server and check one field that answers a real question.

Question: Month-end safeguarding reconciliation shows a small gap. Is it within tolerance, or a shortfall the auditor has to see?
Run the AINumbers MCP tool `run_chain` with {"chain":"cass15-safeguarding-audit-pack"} and read `art-499-check-safeguarding-reconciliation.verdict`.
Re-run with `inputs` for `art-499-check-safeguarding-reconciliation`, reusing the values that result echoed, with `safeguarding_requirement_minor_units` set to 48260000. 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/cass15-safeguarding-audit-pack.html