LangChain launches AI Search in LangSmith to query agent traces in natural language
Overview
LangChain announces AI Search, a feature in LangSmith that finds agent traces by described behavior, such as PII leaks or frustrated users.
A decision model runs over trajectories that SmithDB builds by removing repeated messages from each session. The model reads an 8K token budget filled in priority order, starting with user messages and agent replies.
AI Search is in public beta on LangSmith Cloud in the GCP US, EU, and APAC regions at no additional cost. Org admins turn it on in settings, after which it appears on the tracing page.
Written by AI from the articles below · updated Oct 13, 9:19 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- LangChain BlogOfficialLangChain launches AI Search for querying agent traces in LangSmith
AILangChain announces AI Search, a natural-language way to find agent traces in LangSmith by described behavior, such as PII leaks or frustrated users. The search runs a decision model over trajectories that SmithDB builds by removing repeated messages from each session. The model reads an 8K token budget filled in priority order, starting with user messages and agent replies. AI Search is in public beta on LangSmith Cloud in the GCP US, EU, and APAC regions at no additional cost, and org admins can enable it in settings.
Heat trend
Not enough continuous observations to show a trend yet.