Tag archive
We deployed Langfuse and Arize Phoenix locally, pushed synthetic LLM traces through their OpenTelemetry interfaces, exercised evaluation workflows, and measured the operational cost hidden behind self-hosting.
Originally published on andrew.ooo — visit the original for any updates, code snippets that aged...
DeepLearning.AI's LangChain courses nail the fundamentals, but stop where demos end and production begins. Drawing on two years of shipping RAG systems
A few months ago I built an internal agent on top of Claude Code and the Claude Agent SDK for my...
Using Langfuse to trace multi-step agent workflows, replace custom eval logic, and consolidate LLM observability into one tool that actually scales.
Datadog LLM Observability pricing 2026: 6 levers that cap the bill Summary. Datadog's LLM...
You shipped your AI agent. It answers questions, calls tools, retrieves documents, and mostly does...
Monitoring an AI gateway is crucial for performance, cost, and compliance. This post details eight...
AI agent observability: why HTTP 200 hides wrong answers, the 5 primitives you need, and Braintrust vs Langfuse vs Arize compared.
Use OpenTelemetry to add LLM observability to your Python apps. Follow our guide to trace requests,
OpenTelemetry's CNCF graduation makes standardized AI observability essential for production LLM pipelines. Learn why observability is now baseline operational requirement.
You’ve deployed an LLM agent. It’s live, handling user requests, calling APIs, and reasoning through...