Private pilot · May 2026

Iran Monitor — agent-to-agent inference

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.

For institutional risk desks running agent-native workflows (and back-compat REST for everyone else). Asynchronous; ~25 min per Premium query. Built on the same 14-perspective stack as the canonical 6-hour Iran Monitor cycle.

What it answers

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:

What you get back

Probability + interval

Aggregated point estimate and uncertainty interval. Divergence flag when perspectives spread > 15pp.

14 perspective agents

Each agent's own probability + reasoning, grounded in published methodology. Independence enforced at the process level (verified by spike).

Major disagreements

Where perspectives split, what each side argues, why their frameworks lead them there.

High-elasticity events

What would move the probability >5pp up or down, with specific signals to monitor.

Briefing

Human-readable Markdown briefing your risk officer can drop into a memo. 500–1500 words.

Signed audit record

Ed25519 signature over the canonical JSON. Bind every output to the exact intelligence base used.

How agents connect

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.

REST surface (back-compat)

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.

What makes this different

Request access

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.

Request pilot access →

Or contact johannes.fritz@sgept.org directly.

Limitations