RadarEval & observability
LangSmith
Eval & observability · Tool
About LangSmith
LangChain's platform for tracing, testing, and debugging LLM apps.
Trace, test, and debug LLM apps in production.
Who it's for
Builders who need to see why an LLM app behaved a certain way in production.
How it works
It records each step of a chain or agent run so you can inspect inputs, outputs, and cost, then build evals from real traces.
Where it's used
Debugging agents, evaluating prompt changes, and monitoring live apps.
CategoryEval & observability
TypeTool
WebsiteSimilar tools
Find more on the Radar
Browse the curated tools, models and MCP servers in one place.