---
type: "raw_signal"
id: "search-agent-traces-by-behavior-with-ai-search-2a5046"
slug: "search-agent-traces-by-behavior-with-ai-search-2a5046"
title: "Search agent traces by behavior with AI Search in LangSmith"
description: "LangChain announced AI Search for LangSmith, a natural-language feature for finding agent traces by behavior."
retrieval_nugget: "LangChain announced AI Search for LangSmith, a natural-language feature for finding agent traces by behavior."
observed_at: "2026-10-13"
record_date: "2026-10-13"
date_kind: "observed_at"
why_it_matters: "Source: https://www.langchain.com/blog/agent-traces-ai-search-langsmith"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "langchain.com"
topics: []
entities: ["LangChain","LangSmith","SmithDB","Open SWE"]
related_patterns: []
source_url: "https://www.langchain.com/blog/agent-traces-ai-search-langsmith"
source_urls: ["https://www.langchain.com/blog/agent-traces-ai-search-langsmith"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:search-agent-traces-by-behavior-with-ai-search-2a5046"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/search-agent-traces-by-behavior-with-ai-search-2a5046/","markdown":"https://newruntime.com/signals/search-agent-traces-by-behavior-with-ai-search-2a5046.md","json":"https://newruntime.com/signals/search-agent-traces-by-behavior-with-ai-search-2a5046.json"}
---

# Search agent traces by behavior with AI Search in LangSmith

## Retrieval answer

LangChain announced AI Search for LangSmith, a natural-language feature for finding agent traces by behavior.

LangChain announced AI Search for LangSmith, a natural-language feature for finding agent traces by behavior. Users can search for patterns such as a PII leak, user frustration, or an agent claiming to have completed work it did not complete. Queries can be combined with existing filters, including error status and tags.

The company says AI Search uses a decision model to assess filtered candidate trajectories rather than relying on vector similarity alone. SmithDB normalizes supported trace formats into session trajectories and removes repeated messages. LangSmith assigns each trajectory an 8K-token budget, prioritizing user messages and agent replies before other content; material beyond the budget can be trimmed or dropped.

Source: https://www.langchain.com/blog/agent-traces-ai-search-langsmith

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)