AI Agents · Concept
Observability
LangSmith Observability records an agent's execution as traces made of runs. Enable tracing to debug, evaluate, and monitor agents, while selective tracing and anonymizers control what is recorded.
Last updated
Syntax
export LANGSMITH_AGENT_ID="<your-agent-id>"
export LANGSMITH_AGENT_ENVIRONMENT="local"
export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY="<your-api-key>"In-depth API docs are only for subscribers: parameters, examples, common mistakes and interview practice.
SubscribeRelated
LangSmithLangChainTracertracing_contextanonymizerstracer_session_nameagent addressing