Routing note: For ambiguous user intents, use the shared clarification templates in references/intent-clarification.md.

AI Monitoring

Query AI Gateway request traces, costs, latency, errors, and token usage via the spans query API.

When to Use

Investigate gateway traffic: recent requests, cost breakdowns, error rates, model usage, per-user activity, MCP tool calls, or latency analysis.

When NOT to Use

• User wants to instrument their own application with tracing -> prefer tracing skill (this skill is for querying existing gateway traces, not adding instrumentation)
• User wants to configure gateway models, routing, or rate limits -> prefer ai-gateway skill
• User wants to view application container logs -> prefer logs skill
• User wants to check platform connectivity -> prefer status skill