Cover of Observability for AI Applications
From Keyword to Code

Observability for AI Applications

Tracing, Spans and Debugging a System That Answers Differently Every Time

Trace a Python question-answering service with Langfuse and OpenTelemetry and use the traces to diagnose regressions.

Who it’s for
Developers who can read Python and have called a language-model API.

View on Amazon ↗

Opens Amazon in a new tab. Check the listing for formats and availability.

A closer look

About this book.

Follow a request through retrieval, prompt construction, and model calls. The book builds a cost and latency ledger, traces tools used by an agent, and uses a golden question set to surface changes in answer quality.

Beyond the book

Reader resources.

Download chapter code (ZIP)

Includes a README with setup notes and a chapter-by-chapter file index.

← Back to the books