REST API Reference

List all classifications with filters for risk score and time range.

Get risk distribution statistics (low, medium, high counts).

Get high-risk events above threshold (default: 70).

List all API keys with usage stats.

Create new API key with optional scopes, IP restrictions, expiration.

{
  "name": "Production API",
  "environment": "prod",
  "scopes": ["read", "write", "ingest", "guard"],
  "allowed_ips": ["192.168.1.0/24"],
  "expires_at": "2025-12-31T23:59:59Z",
  "rate_limit_override": 500
}

Rotate a key with optional grace period.

Get usage overview across all keys.

Revoke an API key.

List all guardrails.

Create a guardrail rule.

{
  "name": "Block PII",
  "rule_type": "block_pii",
  "action": "block",
  "config": { "types": ["email", "phone", "ssn"] }
}

Test content against guardrails.

List available detection types for your tier.

Update enabled detections.

Add custom detection with your own prompt.

Upload a compliance framework PDF and auto-generate custom detections.

{
  "pdf_base64": "JVBERi0xLjQK...",
  "framework_name": "My Custom Framework",
  "focus_areas": ["data privacy", "security"],
  "max_controls": 30,
  "auto_save": false
}

Response

{
  "success": true,
  "framework": {
    "name": "GDPR Compliance Framework",
    "description": "EU data protection requirements",
    "summary": "Document covers data subject rights..."
  },
  "controls": [
    {
      "control_id": "GDPR-7.1",
      "name": "Data Subject Access Rights",
      "description": "Users must be able to access their data",
      "category": "Data Rights",
      "evidence_type": "system_check",
      "keywords": ["access request", "data export"]
    }
  ],
  "detections": [
    {
      "id": "gdpr_data_subject_access_rights",
      "name": "GDPR: Data Subject Access Rights",
      "prompt": "Detect violations of compliance control..."
    }
  ],
  "latency_ms": 3500
}

Test a custom detection prompt against sample content.

Get current risk scoring configuration.

Update risk scoring configuration.

{
  "config": {
    "weights": {
      "hallucination": 0.25,
      "policy_violation": 0.25,
      "toxicity": 0.20,
      "pii_detection": 0.15,
      "prompt_injection": 0.15
    },
    "thresholds": {
      "low_max": 35,
      "medium_max": 65
    },
    "compounding": {
      "enabled": true,
      "factor": 1.15,
      "max_multiplier": 1.6
    },
    "min_confidence": 0.6
  }
}

Preview risk score calculation with sample detections.

{
  "detections": [
    { "detection_id": "hallucination", "result": { "hallucination_risk": "medium" }, "confidence": 0.85 },
    { "detection_id": "pii_detection", "result": { "exposure": "low" }, "confidence": 0.9 }
  ],
  "config": { ... }  // optional, uses tenant config if omitted
}

Register a webhook (HTTPS required).

{
  "url": "https://your-app.com/webhook",
  "events": ["alert.critical", "classification.high_risk"]
}

Create integration.

{
  "type": "slack",
  "webhook_url": "https://hooks.slack.com/...",
  "channel_name": "#ai-alerts",
  "events": ["alert.critical", "incident.created"]
}

Test a webhook URL before saving.

List all projects.

Create a new project.

List project API keys.

List project-specific guardrails.

Get project usage statistics.

List incidents with status/severity filters.

Create an incident.

{
  "title": "High hallucination rate detected",
  "description": "Hallucination rate spiked to 15%",
  "severity": "high",
  "incident_type": "hallucination_spike"
}

Update incident status (open, investigating, mitigating, resolved, closed).

Get incident statistics including MTTR.

Get compliance framework status (HIPAA, SOC2, GDPR, PCI-DSS).

Update compliance settings.

{
  "hipaa_enabled": true,
  "gdpr_enabled": true,
  "pii_auto_redact": true,
  "pii_redaction_level": "standard",
  "data_region": "eu"
}

Batch analyze up to 100 interactions. Returns individual results plus summary statistics.

Quick heuristic check if content requires compliance review (no LLM call, instant response).

Create GDPR Data Subject Access Request.

Get model performance leaderboard. Metrics: avg_risk_score, avg_latency_ms, hallucination_rate, error_rate.

Create A/B test comparison between two models.

Get performance history for a specific model.

Create an export job.

{
  "export_type": "events",
  "format": "json",
  "date_from": "2026-01-01T00:00:00Z",
  "date_to": "2026-01-31T23:59:59Z"
}

Download completed export file.

Create a brand safety rule.

{
  "name": "Block Competitor Mentions",
  "rule_type": "competitor_mentions",
  "config": { "terms": ["CompetitorA", "CompetitorB"] },
  "action": "flag",
  "severity": "medium"
}

Check text against brand safety rules.

Create a retention policy.

{
  "name": "Production Events - 90 days",
  "data_type": "inference_events",
  "retention_days": 90,
  "environment_filter": ["prod"]
}

Get retention summary with deletion stats.

Search logs with filters (level, action, actor, resource, time range).

Get log statistics by level and action.

Configure SIEM export (Splunk, Datadog, etc.).

Configure log sampling for high-volume environments.

Configure log retention with optional archiving.

Get usage limits and available models.

Send a message and get AI response with detections.

{
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "What is the capital of France?" }
  ],
  "model": "gemini-flash-lite-latest",
  "runDetections": true
}

List alerts with filtering and pagination.

Query Parameters

Response

{
  "alerts": [
    {
      "alert_id": "a1b2c3d4-...",
      "app_id": "my-chatbot",
      "model": "gpt-4",
      "alert_type": "risk_increase",
      "severity": "critical",
      "current_value": 85.5,
      "baseline_value": 25.0,
      "deviation_percent": 242.0,
      "details": {
        "affected_events": 150,
        "time_window": "1h"
      },
      "created_at": "2025-01-03T10:30:00Z",
      "acknowledged_at": null,
      "acknowledged_by": null,
      "resolved_at": null,
      "resolution_notes": null
    }
  ],
  "summary": {
    "critical": 2,
    "warning": 5,
    "info": 12
  }
}

Acknowledge or resolve an alert.

Request Body

// Acknowledge an alert
{
  "alert_id": "a1b2c3d4-...",
  "action": "acknowledge"
}

// Resolve an alert with notes
{
  "alert_id": "a1b2c3d4-...",
  "action": "resolve",
  "notes": "False positive - expected behavior during deployment"
}

Response

{
  "success": true
}

Get executive-level metrics with period comparisons.

Query Parameters

Response

{
  "period": "7d",
  "health_score": 92.5,
  "summary": {
    "total_events": 150000,
    "total_events_change": 12.5,
    "high_risk_events": 450,
    "high_risk_change": -5.2,
    "avg_latency_ms": 420,
    "sla_compliance_percent": 99.2
  },
  "cost_metrics": {
    "estimated_cost_usd": 1250.00,
    "cost_change": 8.3,
    "monthly_budget_usd": 5000,
    "budget_used_percent": 25,
    "tokens_used": 5000000,
    "cost_per_event": 0.0083
  },
  "incident_metrics": {
    "open_incidents": 2,
    "critical_incidents": 0,
    "mttr_hours": 2.5,
    "incidents_this_period": 5
  },
  "risk_trends": [...],
  "volume_trends": [...],
  "model_breakdown": [...],
  "compliance_status": {...},
  "kpi_status": [...]
}

Get configured KPI targets for the tenant.

Update KPI targets.

{
  "risk_score_target": 25,
  "latency_target_ms": 500,
  "sla_target_percent": 99.5,
  "cost_budget_usd": 5000,
  "mttr_target_hours": 4
}

Export executive report.

{
  "period": "30d",
  "format": "pdf"  // json, csv, pdf
}

Get analytics summary with model performance overview.

Get historical logs filtered by model, environment, or API key.

Get model switch history (when models changed in production).

Auto-detect model switches from inference patterns.

Compare metrics across environments (prod vs staging vs dev).

Capture a snapshot of current environment metrics.

Get model benchmark data with performance rankings.

Get per-API-key analytics showing usage patterns.

Get benchmark comparison report for your industry.

Response

{
  "industry": "fintech",
  "your_metrics": {
    "avg_risk_score": 22.5,
    "avg_latency_ms": 450,
    "hallucination_rate": 2.1,
    "pii_exposure_rate": 0.5
  },
  "industry_benchmarks": {
    "avg_risk_score": { "p25": 18, "p50": 28, "p75": 42 },
    "avg_latency_ms": { "p25": 320, "p50": 480, "p75": 720 },
    "hallucination_rate": { "p25": 1.5, "p50": 3.2, "p75": 5.8 }
  },
  "percentile_rankings": {
    "risk_score": 35,
    "latency": 42,
    "safety": 78
  }
}

List available industries for benchmarking.

Update your tenant's industry for benchmark comparison.

{
  "industry": "healthcare"
}

List available subscription plans with pricing.

Get current subscription and usage details.

{
  "plan": "growth",
  "status": "active",
  "current_period_start": "2026-01-01T00:00:00Z",
  "current_period_end": "2026-02-01T00:00:00Z",
  "usage": {
    "events_ingested": 45000,
    "events_limit": 100000,
    "percent_used": 45,
    "api_keys_used": 3,
    "api_keys_limit": 10
  },
  "features": {
    "custom_detections": true,
    "compliance_reports": true,
    "sla_guarantee": "99.9%"
  }
}

Get usage history across billing periods.

Upgrade to a higher plan tier.

{
  "plan_tier": "pro",
  "billing_cycle": "monthly"
}

Downgrade to a lower plan (takes effect next billing cycle).

List saved playground sessions.

Create a new session.

{
  "name": "Customer Support Test",
  "model": "gemini-flash-lite-latest",
  "system_prompt": "You are a helpful customer support agent."
}

Get session with all messages.

Add a message to the session.

List reusable conversation templates.

Create a template from a session.

{
  "name": "PII Detection Test",
  "description": "Template for testing PII detection",
  "system_prompt": "You are a helpful assistant.",
  "starter_messages": [
    { "role": "user", "content": "My SSN is 123-45-6789" }
  ]
}

Create a new session from a template.

Get session history or list all sessions.

Send a message to the assistant.

Request

{
  "message": "What's my current risk score trend?",
  "session_id": "optional-uuid"
}

Response

{
  "message": "Your risk score has decreased by 12% over the past week...",
  "session_id": "uuid",
  "history": [
    { "role": "user", "content": "What's my current risk score trend?" },
    { "role": "assistant", "content": "Your risk score has decreased..." }
  ]
}

Clear session and start fresh.

Generate a new compliance report.

{
  "framework": "soc2",
  "report_type": "full",
  "date_from": "2026-01-01T00:00:00Z",
  "date_to": "2026-01-31T23:59:59Z",
  "include_evidence": true
}

List generated compliance reports.

Get specific report details.

Export report in various formats.

List custom compliance frameworks.

Create a custom compliance framework.

Analyze a PDF document to extract compliance controls.

Export spans in OpenTelemetry Protocol (OTLP) format.

Query Parameters

Response

{
  "resourceSpans": [{
    "resource": {
      "attributes": [
        { "key": "service.name", "value": { "stringValue": "driftrail" } }
      ]
    },
    "scopeSpans": [{
      "spans": [{
        "traceId": "abc123...",
        "spanId": "def456...",
        "name": "ingest",
        "startTimeUnixNano": "1704534600000000000",
        "endTimeUnixNano": "1704534600500000000",
        "attributes": [
          { "key": "model", "value": { "stringValue": "gpt-4o" } },
          { "key": "risk_score", "value": { "intValue": 25 } }
        ]
      }]
    }]
  }]
}

Push spans to an external OTEL collector.