Logging, Monitoring and Tracing
Structured logs, log pipelines, Prometheus and Grafana for GPU inference, SLO alerting and OpenTelemetry tracing for RAG and agents, with a full observability-stack lab.
0 of 7 complete
- ▶ Up next16 min+50 XPStructured logging for LLM servicesDesign a log schema that answers real operational questions: one JSON event per request, correlation IDs that follow…
- Pro16 min+50 XPLog pipelines, cost and retentionMove logs from containers to storage without losing data or money: collectors (OpenTelemetry Collector, Fluent Bit…
- Pro17 min+50 XPMetrics and dashboards for GPU inferencePrometheus and Grafana applied to LLM serving: metric types, the PromQL you will actually use (error ratio, p95 TTFT…
- Pro17 min+50 XPSLOs, error budgets and alerting that people trustDefine SLIs and SLOs for an LLM service, compute error budgets, write multi-window burn-rate alerts in Prometheus…
- Pro18 min+50 XPDistributed tracing with OpenTelemetryFollow one LLM request across gateway, retrieval, queue, prefill, decode and tools: traces, spans and context…
- Pro14 min+50 XPTracing RAG pipelines and agentsSpan design for retrieval, reranking, generation and tool loops; attributes that make traces debuggable; token and…
- LabPro75 min+100 XPLab: build an observability stackRun Prometheus, Grafana, Loki, Tempo and an OpenTelemetry Collector with Docker Compose, instrument a fake LLM server…