For each funds stream you declare, this answers three questions: are these relevant funds, is the method you assert for them (segregation under CASS 15.3, or an insurance policy or comparable guarantee under CASS 15.5) coherent with the account and instrument facts you supply, and where do the facts you have leave the answer open. Where the answer is judgment required, you get the question, the one input that would resolve it, and who decides, rather than a bare flag. Pairs with the ART-499 Safeguarding Reconciliation Check.
The demo streams below are synthetic and already loaded, so you can press Run without entering anything of your own.
A flag that says only "judgment required" tells a reader that something is unresolved without telling them how to resolve it, which in a supervisory setting is worse than saying nothing. Every judgment this page emits carries three things: what is undetermined, which single input would resolve it, and who decides. The answer to the last one is never this tool. On the receipt-to-segregation deadline in particular, this page reports what you declared and routes the question to judgment rather than asserting a deadline, because that deadline sits in the Electronic Money Regulations and the Payment Services Regulations, which CASS 15.3.1G points to rather than restates.
Pairs with ART-499 CASS 15 Safeguarding Reconciliation Check, which compares your safeguarding requirement against your safeguarding resource for a given as-of date.
Copy this paragraph into Claude, OpenClaw, or any MCP-aware agent to run this exact tool, with this sample, and verify the artifact.
Run the AINumbers MCP tool `classify_safeguarding_method`. Task: Classify each caller-declared funds stream of a UK payment or e-money firm on three questions: whether the funds are relevant funds, whether the safeguarding method asserted for them (segregation under CASS 15.3, or an insurance policy or comparable guarantee under CASS 15.5) is coherent with the designated-account, acknowledgement-letter and instrument facts supplied, and where the supplied facts do not settle the answer.
Call it with arguments: {"policy_parameters":{"as_of_date":"2026-07-29","relevant_funds_high_water_minor_units":4200000,"weeks_observed":60,"streams":[{"stream_ref":"STRM-001","funds_category":"emoney_relevant_funds","method_asserted":"segregation","designated_account_status":"designated_relevant_funds_bank_account","acknowledgement_letter_status":"received_and_countersigned","receipt_to_segregation_timing":"same_business_day"}]}}
Verify before trusting: call `verify_execution_hash` on mcp.ainumbers.co (https://mcp.ainumbers.co/mcp) with the parameter `claimed_hash` set to the returned `execution_hash`, passing the full artifact the run returned (the object containing `policy_parameters` + `output_payload` + `execution_hash`; equivalently `policy_parameters` + `output_payload` with `claimed_hash`), not the bare hash string.
Return the ledger link https://ledger.ainumbers.co/ so a human can re-verify without contacting us.
PII rule: All inputs are processed locally in your browser. No data is transmitted. Do not enter real personal data — use synthetic or anonymised inputs only.
Open the tool with the sample prefilled: https://ainumbers.co/chaingraph/art-500-classify-safeguarding-method.html#p=v1.H4sIAAAAAAAA_wGEAXv-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_smWEAQAA