Observability
LangSmith
How LangSmith connects to the rest of the stack: what it depends on, what depends on it, and what it is commonly deployed alongside.
Concepts it implements
Context compaction
A long conversation or agent trace is summarised and the window restarted from the summary, so the loop can continue past the context limit.
EvalsStructured tests for an LLM system: a fixed input, a run, and grading logic applied to the output, where the grader may be a rule, a rubric, a reference answer, a second model or a person.
Where LangSmith sits
How this component relates to the rest of the stack. Items without a link are not covered here yet.
Alternatives
Solves a similar problem differently
- Langfuse
- Braintrust