Historical scenario stress testing across six named market crises (GFC 2008, COVID 2020, Dot-com bust, Lehman week, Rate Shock 2022, SVB 2023) combined with Monte Carlo stressed paths. Outputs: stressed VaR, stressed ES, max drawdown, recovery-day estimate, and stress multiplier. Chains from QFA-02 (Portfolio VaR) or SIM-03 (Basel RWA). All computation client-side — no portfolio data transmitted.
| Scenario | Equity Shock | Credit Spread | Rate Shock | Vol Multiplier | Horizon |
|---|---|---|---|---|---|
| GFC Peak (Oct 2008) | −42% | +600bps | −200bps | 3.0× | 10d |
| COVID Crash (Mar 2020) | −34% | +300bps | −150bps | 2.8× | 10d |
| Dot-com Bust (2000–02) | −45% | +120bps | −250bps | 2.2× | 20d |
| Lehman Week (Sep 2008) | −10% | +350bps | +50bps | 4.5× | 5d |
| Rate Shock (2022) | −20% | +180bps | +400bps | 1.8× | 20d |
| SVB Contagion (Mar 2023) | −30% | +200bps | +50bps | 2.4× | 5d |
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 `compute_stress_test_scenarios`. Task: Run multi-scenario stress tests across a portfolio and returns a structured risk_parameter mandate with P&L impact and regulatory capital implications.
Call it with arguments: {"policy_parameters":{}}
Verify before trusting: this node computes in your browser, so the MCP endpoint returns no execution_hash. Run the tool in the page, export the Policy Mandate artifact it produces, and call `verify_execution_hash` on mcp.ainumbers.co (https://mcp.ainumbers.co/mcp) with that artifact.
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/qfa-03-stress-test-engine.html#p=v1.H4sIAAAAAAAA_wECAP3_e31Dv6ajAgAAAA