SYSTEM R AI

Platform Guardian

Real-time platform monitoring, health status, and agent issue reporting.

Overview

The Platform Guardian is System R's monitoring and security layer. It tracks platform health, detects anomalies, and provides agents with a way to report issues they encounter.

Platform status (public)

GET /v1/guardian/status

No authentication required. Use this as a health check endpoint.

curl https://agents.systemr.ai/v1/guardian/status
{
  "platform": "System R",
  "status": "operational",
  "uptime_seconds": 864000,
  "latency_ms": 12,
  "version": "2.1.0"
}
FieldDescription
statusPlatform status: operational, degraded, maintenance.
uptime_secondsSeconds since last restart.
latency_msCurrent API latency in milliseconds.
versionCurrent platform version.

Report an issue

POST /v1/guardian/report

Agents can report issues they encounter during operation. No admin authentication required. Use your agent_id to identify the report.

Request

curl -X POST https://agents.systemr.ai/v1/guardian/report \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "agt_a1b2c3d4",
    "report_type": "error",
    "description": "calculate_kelly returned empty result for valid input",
    "details": {
      "tool_name": "calculate_kelly",
      "input_count": 10,
      "error_message": "Division by zero"
    }
  }'

Parameters

ParameterTypeRequiredDescription
agent_idstringYesYour agent ID.
report_typestringYesType: error, degradation, suspicious_activity.
descriptionstringYesHuman-readable description of the issue.
detailsobjectNoAdditional context (tool name, error messages, etc.).

Response

{
  "event_id": "evt_xyz789",
  "status": "recorded"
}

Report types

TypeWhen to use
errorA tool returned an unexpected error or incorrect result.
degradationResponse times are notably slower than usual.
suspicious_activityUnexpected behavior that might indicate a security issue.

Admin endpoints

The following endpoints require admin authentication via the X-Admin-Key header. These are for platform operators, not agents.

Security events

GET /v1/guardian/events
ParameterDescription
limitMax events to return (default 100, max 1000).
categoryFilter by event category.
severityFilter by severity level.

Active alerts

GET /v1/guardian/alerts

Returns CRITICAL and EMERGENCY severity events. Max 500 entries.

System metrics

GET /v1/guardian/metrics

Returns uptime, error rate, latency percentiles, and event counts.

Monitoring your agent

While the Guardian monitors the platform, you can monitor your own agent's health using:

  • GET /v1/billing/balance to check credit balance
  • GET /v1/audit/trail to review recent activity
  • GET /v1/audit/compliance-check to run compliance analysis
  • GET /v1/billing/usage to review spending by operation
System R AI
Python SDKpip install systemr
MCP Serveragents.systemr.ai/mcp/sse
OpenAPI Specagents.systemr.ai/openapi.json
Machine Docsagents.systemr.ai/llms.txt
GitHubSystem-R-AI
X@Systemrai
YouTube@systemr_ai
Emailhello@systemr.ai
Phone628 333 6693
Address7901 4TH ST N, STE 28529, ST PETERSBURG, FL 33702
TermsTerms of Service
PrivacyPrivacy Policy
SecuritySecurity Policy
© 2026 System R AI. Software platform. Not financial advice.

On this page