Comparison
LangSmith vs Span
LangSmith and Span are both common AI/LLM terms but cover different ideas. Here is a quick side-by-side.
When you would reach for LangSmith
LangSmith comes up when the question is fundamentally about infrastructure.
A LangChain app with one line of setup: every chain run shows up in the LangSmith trace UI with input, output, intermediate steps, and per-step costs.
When you would reach for Span
Span comes up when the question is fundamentally about infrastructure.
An LLM span: model=gpt-4o, input=system+user msgs, output=response text, tokens_in=820, tokens_out=410, latency=1.8s, cost=$0.0061.
Frequently asked
What is the difference between LangSmith and Span?
LangSmith: LangSmith is LangChain's commercial LLM observability and evaluation platform. It captures traces (LangChain-native and OTel), runs evaluations, manages prompt versions, and supports dataset curation. Span: A span is a single unit of work within a trace — one LLM call, one tool call, one retrieval — with a start time, end time, attributes (model, tokens, cost), and a parent span that links it into the trace tree.
When should I use LangSmith vs Span?
LangSmith is the right concept when you are focused on infrastructure. Span applies when you are focused on infrastructure.
Are LangSmith and Span the same thing?
No. LangSmith is infrastructure; Span is infrastructure. They are related but address different parts of the AI stack.