observability▌

Read the setup guide before making changes:

Answer user questions about monitoring LLMs and agentic components using data ingested into Elastic only. Focus on LLM performance, cost and token utilization, response quality, and call chaining or agentic workflow orchestration. Use ES|QL, Elasticsearch APIs, and (where needed) Kibana APIs. Do not rely on Kibana UI; the skill works without it. A given deployment typically uses one or more ingestion paths (APM/OTLP traces and/or integration metrics/logs)— discover what is available before query

Open-source AI observability and evaluation platform for LLM applications with tracing, evaluation, datasets, experiments, and real-time monitoring.

Comprehensive monitoring setup with metrics collection, log aggregation, alerting, and health checks. \n \n Covers Prometheus for metrics instrumentation, Grafana dashboards for visualization, and structured logging with Winston for log aggregation \n Includes pre-built alert rules for high error rates, slow response times, pod failures, and resource saturation \n Provides advanced health check endpoints that test database, cache, and external API dependencies with latency tracking \n Implements

Query metrics, logs, and traces across Azure Monitor, Application Insights, and Log Analytics. \n \n Access metrics, KQL log queries, and distributed tracing through MCP tools or Azure CLI commands \n Supports Application Insights for APM and performance analysis, Log Analytics for custom KQL queries, and Azure Monitor for infrastructure metrics \n Includes common KQL query patterns for errors, request performance, and resource usage monitoring \n Workbooks integration for building interactive o

Query metrics, logs, and traces across Azure Monitor, Application Insights, and Log Analytics. \n \n Access Azure Monitor metrics, Application Insights APM data, and Log Analytics KQL queries through MCP tools or Azure CLI commands \n Supports distributed tracing, performance analysis, and infrastructure monitoring across applications and resources \n Includes interactive workbooks for building custom dashboards and reports on observability data \n Common use cases: error tracking, request perfo

ln-627-observability-auditor