Home / Case studies
The register
Published seven case studies connecting the system's engineering decisions to Tier 1 banking regulation. Each record has a number, the regulation it maps to, its status and its publication date.
| No. | Record | Domain | Regulation | Status | Published | Read |
|---|---|---|---|---|---|---|
| CS-01 | A Telegram channel, hardened like a production banking gateway. Eighteen controls in five layers: gateway, identity, session isolation, behavioural rules and operations. The same hardening pattern bank procurement committees ask architects to apply to third-party chat channels. |
Security | Security | Production | 19 April 2026 | ~9 min |
| CS-02 | Agentic KYC - unravelling corporate UBO across jurisdictions. Enhanced CDD, adverse-media screening, and beneficial-ownership unwind under AMLR Article 42 and the BORIS register. Research swarms and vision agents as proof-of-build components - the AFC transformation shape banks are budgeting for in 2026. |
Anti-Financial Crime | AMLR | Architecture | 21 April 2026 | ~10 min |
| CS-03 | Multi-model orchestration without vendor lock-in. Nexus routes across GLM, MiniMax, Birch, Gemma, and Claude with a fallback chain that survives a provider outage mid-task. The vendor-independence pattern DORA Article 28 now asks banks to design for. |
Orchestration | DORA | Production | 22 April 2026 | ~10 min |
| CS-04 | Agentic AI across the consumer-lending lifecycle. Origination through servicing - PSD2/3 data aggregation, document ingestion at application time, affordability beyond traditional credit scoring, real-time decisioning, back-book repricing. Same component-level proof-of-build anchoring under PSD3 and AI Act Annex III. |
Lending | PSD3 AI Act | Architecture | 25 April 2026 | ~11 min |
| CS-05 | Cron-Driven Autonomy The operational layer that keeps a multi-agent system honest while nobody is watching - the upgrade pipeline, the verification discipline, and the guardrails under DORA Art. 17. |
Autonomy | DORA | Production | 22 May 2026 | ~11 min |
| CS-06 | When the watcher couldn't be trusted. A model-failover watcher that flipped a healthy system onto a fallback in a tight loop - because the cloud was rate-limiting, not failing. The boundary between monitoring and decision-making under AI Act Article 14. |
Oversight | AI Act | Production | 22 May 2026 | ~9 min |
| CS-07 | The bleed - AI compute as a treasury function. Two paid-API leaks caught by a balance poller on a daily timer. The forensics, the two rules that fell out, the observer-based circuit breaker that enforces them, and the case for treating production agentic compute as a treasury function. |
Cost Governance | Governance | Production | 25 May 2026 | ~11 min |
Production: running in Nexus. Architecture: a design built from components that run in Nexus.