{"product_id":"observability-for-llm-applications-gabriel-anhaia-9798257519970","title":"Observability for LLM Applications: Tracing, Evals, and Shipping AI You Can Trust","description":"\u003cb\u003eYour LLM feature went out at 2 a.m. last Thursday. Latency is fine. Error rate is zero. And somewhere, quietly, it is lying to a customer.\u003c\/b\u003e \u003cp\u003e\u003c\/p\u003eTraditional observability cannot see this. CPU graphs, HTTP status codes, and p99 dashboards were built for systems that either work or crash. LLMs do neither. They return a confident sentence, the span closes green, and the failure lives in the content. \u003cp\u003e\u003c\/p\u003eIf you ship LLM features in production - as a backend engineer, a platform engineer, an SRE who inherited someone else's prompt - this book is the operational handbook you have been missing. It is not a theory book about transformers. It is not a prompt engineering tour. It is the stack you actually need on Monday morning to know your AI works. \u003cp\u003e\u003c\/p\u003e\u003cb\u003eWhat you get: \u003c\/b\u003e the three new pillars (traces, evals, cost and drift metrics), built first on vendor-neutral \u003ci\u003eOpenTelemetry GenAI semantic conventions\u003c\/i\u003e, then layered with the tools that matter in 2026 - \u003ci\u003eLangfuse\u003c\/i\u003e, \u003ci\u003eLangSmith\u003c\/i\u003e, \u003ci\u003eArize Phoenix\u003c\/i\u003e, \u003ci\u003eBraintrust\u003c\/i\u003e, \u003ci\u003eDeepEval\u003c\/i\u003e, \u003ci\u003eHelicone\u003c\/i\u003e, and a roll-your-own OTel Collector + ClickHouse + Grafana stack for teams that want everything in-house. Every tool gets an honest verdict: what it is best at, what it is bad at, when to pick it, what it costs. \u003cp\u003e\u003c\/p\u003eYou will learn how to capture a full LLM decision path as a trace, run evals continuously in CI and in production, track token cost per user and per feature, detect drift before your users do, and write incident response runbooks for a failure mode your pager has never seen. Real code in Python, Go, and TypeScript. Real dashboards. Real traces. \u003cp\u003e\u003c\/p\u003e\u003cb\u003eComplementary to\u003c\/b\u003e Hamel Husain's \u003ci\u003eEvals for AI Engineers\u003c\/i\u003e (O'Reilly, 2026): where that book goes deep on eval methodology for ML engineers, this one covers the wider operational stack - tracing, tooling, cost, drift, and on-call - for the platform-engineer reader. \u003cp\u003e\u003c\/p\u003eBy the end, you will have a production-readiness checklist you can run against your own system and mean it when you tell your boss the answer is yes. The first chapter starts with a real incident. Monday morning, you will have something to do. \u003cp\u003e\u003c\/p\u003e\u003ci\u003eBook 1 of The AI Engineer's Library.\u003c\/i\u003e\u003cbr\u003e\u003cbr\u003e\u003cb\u003eAuthor:\u003c\/b\u003e Gabriel Anhaia\u003cbr\u003e\u003cb\u003eISBN-13:\u003c\/b\u003e 9798257519970\u003cbr\u003e\u003cb\u003ePublisher:\u003c\/b\u003e Independently Published\u003cbr\u003e\u003cb\u003eLanguage:\u003c\/b\u003e English\u003cbr\u003e\u003cb\u003ePublished:\u003c\/b\u003e 04\/15\/2026\u003cbr\u003e\u003cb\u003ePages:\u003c\/b\u003e 340\u003cbr\u003e\u003cb\u003eFormat:\u003c\/b\u003e Paperback\u003cbr\u003e\u003cb\u003eWeight:\u003c\/b\u003e 1.00lbs\u003cbr\u003e\u003cb\u003eSize:\u003c\/b\u003e 9.00h x 6.00w x 0.71d","brand":"Gabriel Anhaia","offers":[{"title":"Paperback","offer_id":49084151890175,"sku":"9798257519970","price":24.99,"currency_code":"USD","in_stock":true}],"url":"https:\/\/www.whiterainbookhouse.com\/products\/observability-for-llm-applications-gabriel-anhaia-9798257519970","provider":"WR Book House","version":"1.0","type":"link"}