Record · corpus.blog/posts/01a0877d-9a5c-711a-a630-ab606b98d17d

Observability for LLM Systems: Metrics, Traces, Logs, and Testing in Production

glukhov.org · published 28 February 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at glukhov.org Wayback capture

0blogs citing

First cited: —
Most recent: —
Rank this month: not ranked
External links: 18
Words captured: 3,971

Cited by

No blog we hold has cited this post yet.

Links from this post

Link

Host

https://prometheus.io/docs/prometheus/latest/configuration/configuration/

prometheus.io

https://prometheus.io/docs/instrumenting/exposition_formats/

prometheus.io

https://prometheus.io/docs/practices/instrumentation/

prometheus.io

https://prometheus.io/docs/practices/naming/

prometheus.io

https://prometheus.io/docs/practices/histograms/

prometheus.io

https://prometheus.io/docs/prometheus/latest/configuration/alerting_rules/

prometheus.io

https://prometheus.io/docs/alerting/latest/overview/

prometheus.io

https://prometheus.io/docs/alerting/latest/configuration/

prometheus.io

https://grafana.com/docs/grafana/latest/visualizations/dashboards/build-dashboards/view-dashboard-json-model/

grafana.com

https://grafana.com/docs/grafana/latest/administration/provisioning/

grafana.com

https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/user_guide/metrics.html

docs.nvidia.com

https://docs.pytorch.org/serve/metrics_api.html

docs.pytorch.org

https://docs.nvidia.com/datacenter/dcgm/latest/gpu-telemetry/dcgm-exporter.html

docs.nvidia.com

https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack

github.com

https://prometheus-operator.dev/docs/developer/getting-started/

prometheus-operator.dev

https://opentelemetry.io/docs/specs/otel/metrics/sdk_exporters/prometheus/

opentelemetry.io

https://prometheus.io/docs/guides/opentelemetry/

prometheus.io

https://docs.langchain.com/langsmith/trace-with-opentelemetry

docs.langchain.com

Elsewhere on glukhov.org (12)

AI Assistant Architecture: LLM, Memory, Tools, Routing, Observability Read at the source ↗

glukhov.org

https://www.glukhov.org/observability/

glukhov.org

Prometheus Monitoring: Complete Setup & Best Practices Read at the source ↗

glukhov.org

Polling Agents in AI Assistants: 11 Implementation Patterns Read at the source ↗

glukhov.org

A2A vs MCP: Do AI Agents Really Need Both Protocols? Read at the source ↗

glukhov.org

Multi-Agent Orchestration Patterns: A Practical Guide Read at the source ↗

glukhov.org

Google A2A Protocol in 2026: Adoption, Hype, and Reality Read at the source ↗

glukhov.org

What Is the A2A Protocol? Agent Cards and Tasks Explained Read at the source ↗

glukhov.org

A2A Streaming and Async Tasks for Long-Running Agent Workflows Read at the source ↗

glukhov.org

https://www.glukhov.org/llm-performance/

glukhov.org

https://www.glukhov.org/llm-hosting/

glukhov.org

https://www.glukhov.org/rag/

glukhov.org