AI engineering glossary · MLOps, LLMOps cloud
What is LLM observability?
LLM observability: Monitoring and tracing applications built on language models by capturing each prompt, response, retrieved document, tool call, token count, latency and cost, linked into one trace. It lets teams debug bad answers and control spending.
LLM observability: an example
A trace shows that a wrong answer came from a retrieval step returning an outdated policy document.
Related terms
More MLOps, LLMOps cloud terms
Where you learn it
LLM observability is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.