One-minute route into Agenda Intelligence — an open-source AI-skill portfolio for structured strategic-risk analysis. For fund analysts, compliance and sanctions desks, journalists, advisory shops, and AI builders embedding regional intelligence into agents.
Use for EDD evidence readiness around ownership, sanctions exposure, transit, payments, and human-review routing.
Run CIS Exposure GateA four-repo system for AI agents producing auditable strategic-risk analysis — not generic geopolitical summaries.
[primary] / [secondary] / [user-provided] / [inference] / [analyst-judgment]) and optional action flags ([verify], [stale-risk: YYYY-MM]).live-source-backed, user-provided sources, illustrative source packet, reasoning-only. Each example states its mode openly.| Role | Repo | What it covers |
|---|---|---|
| Horizontal reasoning skill | Global Think Tank Analyst | Cross-domain policy-risk memo structure: sanctions, regulatory, geopolitical, trade, scenario and red-team modes. |
| Vertical: Central Asia + Caspian | central-asia-caspian-hybrid-intelligence-skill | Sanctions, AML, banking, beneficial-ownership opacity, corridor logistics and energy risk across Kazakhstan, Uzbekistan, Azerbaijan, Turkmenistan, Kyrgyzstan, Tajikistan and the Caspian. |
| Vertical: Gulf + Middle East | gulf-middle-east-hybrid-intelligence-skill | Iran sanctions and OFAC SDN exposure, GCC banking and sovereign wealth (PIF, ADIA, Mubadala, QIA, KIA), energy and OPEC+ dynamics, Hormuz / Bab-el-Mandeb / Red Sea maritime chokepoint risk. |
| Evidence + audit layer | Agenda Intelligence MD | Validation, JSON schemas, evidence audit, scoring rubrics, CLI and MCP tooling so strategic-intelligence agent output can be audited rather than only read. |
The reasoning portfolio also runs as deployed vertical workers on Cloudflare. The browser demo currently kept public is the CIS counterparty EDD flow — enter a real-shaped case and the live worker returns a structured evidence-readiness triage. Free, no login.
Evidence triage only, not advice; human review required. Illustrative usage, no paying customers.
Try this prompt block you can paste into Claude or Codex against your own scenario.STATUS.md with a Bar 1 / Bar 2 Definition-of-Done; Bar 2 cleared for agent integration as of 2026-05-21, with practitioner review (B2.8) remaining an optional, audience-gated trust layer. The horizontal Global Think Tank Analyst repo uses a different maturity framework — VALIDATION_PLAN.md, practitioner-review-first; zero external reviews recorded so far. If you are a sanctions, AML, energy-trading, shipping, Gulf-banking, Central-Asia-corridor, Iran-watcher, or EU trade-policy practitioner and would consider reviewing a case packet, open an issue on the relevant repo or email below.