shadow-mentor

5-voice AI compliance council for regulated loan origination. 11 MCP tools (loan_council, loan_council_typed, risk_tools, recall, calibration, scenarios, traceability, verify_attestation, banking_profile, disparity, size_position). FICO < 700 is a hardcoded JS conditional with pinned tests. Strict-JSON enum verdicts. AA01–AA05 adverse-action codes per CFPB Circular 2026-03. MCPTox / OX Security 2026 named-threat coverage mechanically tested.

AML/KYC Investigator persona for BSA, OFAC SDN + 50% rule, USA PATRIOT §326 CIP, FinCEN CDD, and FATF high-risk-jurisdiction screening. Hard-blocks on sanctions hit or unverified identity. Escalates on structuring, PEP, opaque beneficial ownership, GTOs. Every finding cites the specific rule. ACAMS 2026 procurement-lane persona.

Verify a Shadow attestation record (Ed25519 or HMAC) without leaving Claude Desktop. Confirms request wasn't tampered, response wasn't tampered, the exact pinned model ran, and the deployment key material matches. Use when a bank auditor hands you a persisted JSON response and asks "is this real." Works cross-language — Python shadow-verify library produces byte-identical results for the same inputs on Python 3.9–3.13.

Bank-grade compliance-officer persona for AI-mediated lending, HR, or regulated-industry decisions. Cites CFPB Circular 2026-03, SR 26-2 footnote 3 delegation positioning, ECOA / Reg B / Fair Housing Act, USA PATRIOT §326 CIP, FinCEN CDD, OFAC. Refuses to approve without human review. Never invents thresholds not in checked-in policy.

Customer-Advocate persona for adverse-action notice quality control. Reviews explanation readability under CFPB Circular 2026-03 model-traceability. Escalates on any adverse-action reason present. Never blocks — human-review path, not veto path.

Run a 5-voice data-science governance council on an ML artifact reference. Data Steward (drift), Model Validator (calibration), Fair-ML Auditor (EEOC 80% rule, always blocks on violation), Reproducibility Critic (metadata completeness), Ops Realist (p95 latency). Returns SHIP / REWORK / BLOCK with per-voice rationale. Pure computation — no LLM. Use before shipping any ML pipeline that will make consumer-facing decisions.

Macro-Contrarian persona for sector-cycle + recession-sensitivity dissent. Provides counter-narrative even when other voices approve. Escalates on commercial real estate exposure; advisory-only on other sectors. Never blocks — dissent voice, not veto voice.

5-to-6 voice AI compliance council for regulated lending. Deterministic verdict in milliseconds. Signed Ed25519 attestation. Runs in your VPC. Cites CFPB / SR 26-2 / ECOA / Reg B / BSA / OFAC / FinCEN CDD by construction. Pure-compute pass — no LLM in the tool body.

Institutional Risk Officer persona for portfolio VaR, LTV, concentration, and sector exposure decisions. Cites Addendum C — Risk Appetite Note. Never approves when VaR exceeds ceiling; escalates on borderline concentration or single-name limits. Loredana-anchored thresholds (LTV 0.80, VaR 0.12 @95%/10d).

Size a trading position with FinPos discipline. Takes a direction from an upstream Judge (long / short / no_op), a bankroll, a volatility regime, and Kelly parameters — returns a fund/skip verdict with Kelly-cap- respecting, drawdown-adjusted position size. Never emits a direction (that's the Judge's job upstream). Cross-vertical wire format identical to the Orallexa Python engine so banking + trading audit trails share one schema.