Skip to main content

Production

Deploy OmniCoreAgent with confidence. Runtime usage metrics and guardrails.

Examples


📊 Metrics & Observability

Track everything your agent does:
Available Metrics:
  • total_requests — Number of agent.run() calls
  • total_tokens — Total tokens used (input + output)
  • total_request_tokens — Tokens sent to LLM
  • total_response_tokens — Tokens received from LLM

🛡️ Guardrails

Protect against prompt injection attacks:
Guardrails Detect:
  • Prompt injection attempts
  • Jailbreak attempts
  • System prompt extraction attempts
  • Role manipulation attacks

🔧 Usage Limits

Set limits to prevent runaway request or token usage:

Previous: Background Agents — Scheduled autonomous tasks