← Glossary / 05 of 100
n. / AI agents
LLM observability
Definition
LLM observability is the practice of recording traces, model calls, tool calls, cost, latency, and errors for LLM-powered applications so their behavior can be inspected and debugged in production.
In more detail
Unlike traditional application logging, LLM observability keeps prompts, model outputs, token usage, and quality evidence attached to the run that produced them, since a single user-visible answer can depend on several chained model and tool calls.
Related terms
