LLM Application Observability with OpenTelemetry: Traces, Tokens, Cost and Quality

Instrument LLM applications with OpenTelemetry and the GenAI conventions: spans per call and per RAG step, token and latency metrics, cost per feature, evaluations linked to traces, and prompt privacy.

36 minutes read

Josue Puig

2026-10-21

0 views

opentelemetry

LLM

observabilidad

Busqueda Vectorial

Premium resource

LLM Application Observability with OpenTelemetry: Traces, Tokens, Cost and Quality. Sign in with an eligible account to read this resource. New subscriptions are not available yet.

Loading comments...

Related Resources

Tutorial

Tutorial: Introduction to LangChain

Learn the basics of LangChain to build AI applications. From installation to your first functional pattern.

Guía

PREMIUM

Context Engineering for AI Agents: Compaction, External Memory, and Subagents

Manage AI agent context with compaction, external memory, selective retrieval, and bounded tool results.

Guía

Guide: RAG in Production — Chunking, Embeddings, Hybrid Search, and Reranking

Battle-tested patterns for building production-ready RAG (Retrieval-Augmented Generation) systems in 2026: semantic chunking, embedding selection, hybrid search, and cross-encoder reranking.