Search agent traces by behavior with AI Search in LangSmith
3.24T1.5 sourceLangChain Blog
Source record
Published by LangChain Blog (T1.5 source). The original is at https://www.langchain.com/blog/agent-traces-ai-search-langsmith.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryLangSmith launched AI Search, a natural-language interface for querying agent traces, built on SmithDB, a database designed for trace data. It complements Custom Apps and aims to make it easier to find traces for eval datasets, annotation queues, and debugging.
Why it mattersDirect product detail on a new way to mine large, unstructured agent traces — relevant to teams using LangSmith for eval and annotation workflows.

Cited by
No citations on record.
