An A2A-compliant agent that assesses novel Iran-conflict scenarios. Submit a scenario; get a probability, per-framework reasoning, and a signed audit record drawn from a verified intelligence base.
Beyond the 8 canonical scenarios our cron-driven monitor tracks, you can submit a bespoke scenario and have it assessed through 14 independent perspective agents — Tetlock-style superforecasting, Schelling bargaining, Wack predetermined-elements analysis, plus domain lenses on IRGC, regional security, nuclear posture, and US-policy options.
Example queries pilot buyers have asked:
Aggregated point estimate and uncertainty interval. Divergence flag when perspectives spread > 15pp.
Each agent's own probability + reasoning, grounded in published methodology. Independence enforced at the process level (verified by spike).
Where perspectives split, what each side argues, why their frameworks lead them there.
What would move the probability >5pp up or down, with specific signals to monitor.
Human-readable Markdown briefing your risk officer can drop into a memo. 500–1500 words.
Ed25519 signature over the canonical JSON. Bind every output to the exact intelligence base used.
Point your A2A-native agent stack — Claude, LangChain's A2A integration, Spring AI, IBM watsonx, or anything that speaks the A2A spec — at https://iran-a2a.globaltradealert.org. Discovery via Agent Card; one skill exposed (assess_scenario); streaming on; Bearer-token auth.
GET https://iran-a2a.globaltradealert.org/.well-known/agent-card.json
↓
{
"name": "iran-monitor",
"url": "https://iran-a2a.globaltradealert.org",
"skills": [{ "id": "assess_scenario", "...": "..." }],
"capabilities": { "streaming": true, "pushNotifications": false },
"securitySchemes": { "bearer": { "type": "http", "scheme": "Bearer" } }
}
Submit a scenario as an A2A Message via JSON-RPC:
POST https://iran-a2a.globaltradealert.org/v1/jsonrpc
Authorization: Bearer <pilot-key>
Content-Type: application/json
{
"jsonrpc": "2.0", "id": 1, "method": "message/send",
"params": {
"message": {
"role": "user",
"parts": [{ "kind": "text", "text": "Iran (IRGC or proxy) launches a meaningfully disruptive cyber attack on German critical infrastructure within the next 30 days, with German government public attribution." }],
"data": { "horizon": "30d", "tier": "premium", "deliver_to": "risk-desk@your-fund.com" }
}
}
}
↓
A2A Task { "id": "...", "status": { "state": "submitted" }, ... }
For streaming progress, hit /v1/jsonrpc/stream with message/stream and consume Server-Sent Events (TaskStatusUpdateEvent + TaskArtifactUpdateEvent per the A2A spec). The final artifact carries the briefing, structured per-perspective outputs, and the signed audit record.
For pilots whose stacks aren't A2A-native yet, the same backend speaks plain REST:
POST https://iran-a2a.globaltradealert.org/v1/queries
Authorization: Bearer <pilot-key>
Content-Type: application/json
{
"scenario": "Iran (IRGC or proxy) launches a meaningfully disruptive
cyber attack on German critical infrastructure within
the next 30 days, with German government public attribution.",
"horizon": "30d",
"tier": "premium",
"deliver_to": "risk-desk@your-fund.com"
}
↓
202 Accepted: { "query_id": "...", "estimated_completion_utc": "..." }
Poll GET /v1/queries/{id} until status: "completed" (~25 min for Premium). Same response payload as the A2A path.
See ONBOARDING.md for the full integration menu — A2A-native, Python SDK, REST + curl, and the LLM-tool pattern.
Pilot access is currently limited to institutional risk desks (hedge funds, sovereign wealth, commodities, reinsurance). Send a short note describing your use case and we'll respond within two business days.