Skip to content

SAGE Chat

SAGE (Sovereign AI Governance Engine) is BreachSpider's AI reasoning engine for ICS/OT vulnerability analysis. The chat endpoint provides an interactive Q&A interface grounded in the BreachSpider CVE corpus.

Endpoint

POST /api/v1/chat

Requires Professional tier or above.

Request

curl -X POST \
  -H "Authorization: Bearer bs_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "message": "What are the top 5 critical CVEs affecting Siemens S7-1500 PLCs published in 2025?",
    "context": {
      "environment_id": 5
    }
  }' \
  "https://breachspider.com/api/v1/chat"

Response

{
  "api": { "version": "1.0.0", "request_id": "bs-req-...", "processing_ms": 2341 },
  "data": {
    "message": "Based on the BreachSpider corpus, the top 5 critical CVEs...",
    "sources": [
      {
        "cve_id": "CVE-2025-38484",
        "title": "Siemens SIMATIC S7-1500 Memory Corruption",
        "cvss_score": 9.8,
        "url": "https://breachspider.com/ics-cve/CVE-2025-38484"
      }
    ],
    "confidence": 0.91,
    "model": "SAGE-v1"
  }
}

SAGE Confidence Tiers

Tier Score Range Meaning
SOVEREIGN_AUDIT_PASS 0.90-1.00 Mathematically traced to source data
HIGH_CONFIDENCE 0.75-0.89 Strong grounding with minor inference
MODERATE 0.50-0.74 Mixed grounding, verify key claims
LOW Below 0.50 Significant inference, use with caution

Rate Limits

SAGE queries are metered separately from API calls.

Tier SAGE queries/month
Professional 500
API Unlimited
Enterprise Unlimited