---
type: "post"
id: "search-agent-traces-by-behavior-with-ai-search-85f6f8"
slug: "search-agent-traces-by-behavior-with-ai-search-85f6f8"
title: "Search agent traces by behavior with AI Search in LangSmith"
description: "Thesis: Behavior-based trace search can shift agent observability from manually locating examples to querying for operationally meaningful cases."
retrieval_nugget: "Thesis: Behavior-based trace search can shift agent observability from manually locating examples to querying for operationally meaningful cases."
published_at: "2026-10-13"
updated_at: "2026-10-13"
record_date: "2026-10-13"
date_kind: "published_at"
topics: ["agent-observability"]
source_urls: ["https://www.langchain.com/blog/agent-traces-ai-search-langsmith"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:search-agent-traces-by-behavior-with-ai-search-85f6f8"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:e1ea10a4f09f75b45d30cbda90f8074fdc4a88caff6d426e227600e7bf621605","reviewed_at":"2026-10-13T13:00:52.502Z","source_evidence_count":1,"verified_claim_count":2,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":2,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Behavior-based trace search can shift agent observability from manually locating examples to querying for operationally meaningful cases.","observed_facts":[{"text":"LangSmith AI Search accepts natural-language descriptions of behaviors such as PII leakage, user frustration, or an agent claiming success without completing a task.","source_urls":["https://www.langchain.com/blog/agent-traces-ai-search-langsmith"]},{"text":"LangSmith says SmithDB normalizes supported trace formats into session trajectories and AI Search assigns each an 8K-token budget, prioritizing user messages and agent replies.","source_urls":["https://www.langchain.com/blog/agent-traces-ai-search-langsmith"]}],"mechanism":"LangSmith filters candidate traces and has a decision model inspect each remaining trajectory against the natural-language description, rather than relying on a compressed embedding to distinguish what happened.","why_now":"The source says fast decision models have made this kind of narrow question affordable and quick enough to run at search time, addressing a prior speed-and-cost constraint.","implications":["Teams can surface examples for debugging, evaluation datasets, or reviewer queues without first defining an evaluator or reading traces manually.","More surfaced cases may increase human review capacity, but the feature does not establish that matches are complete or correct."],"evidence_boundary":"These capabilities and implementation details are described in LangChain's product announcement; the source does not provide independent accuracy, latency, or cost measurements for AI Search.","watch_conditions":["Whether LangChain publishes measured search quality and latency across trace types, especially for behaviors whose evidence falls outside the retained 8K-token budget."],"related_records":[],"new_branch_reason":"No prior New Runtime record was supplied; this records a specific search interface and its stated implementation limits without assuming a prior pattern record."}
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/posts/search-agent-traces-by-behavior-with-ai-search-85f6f8/","markdown":"https://newruntime.com/posts/search-agent-traces-by-behavior-with-ai-search-85f6f8.md","json":"https://newruntime.com/posts/search-agent-traces-by-behavior-with-ai-search-85f6f8.json"}
---

# Search agent traces by behavior with AI Search in LangSmith

## Retrieval answer

Thesis: Behavior-based trace search can shift agent observability from manually locating examples to querying for operationally meaningful cases.

Thesis: Behavior-based trace search can shift agent observability from manually locating examples to querying for operationally meaningful cases.

Observed fact: LangSmith AI Search lets users describe behaviors such as PII leakage, user frustration, or an agent claiming success without completing a task. Observed fact: the release says SmithDB converts supported trace formats into session trajectories, removing repeated messages, and AI Search applies an 8K-token budget that prioritizes user messages and agent replies.

Mechanism: LangSmith filters candidate traces and has a decision model inspect each remaining trajectory against the natural-language description, rather than relying on a compressed embedding to distinguish what happened. Why now: The source says fast decision models have made this kind of narrow question affordable and quick enough to run at search time, addressing a prior speed-and-cost constraint.

First implication: Teams can surface examples for debugging, evaluation datasets, or reviewer queues without first defining an evaluator or reading traces manually. This could increase the number of relevant cases available for human review, but it does not itself establish that the model's matches are complete or correct.

Evidence boundary: These capabilities and implementation details are described in LangChain's product announcement; the source does not provide independent accuracy, latency, or cost measurements for AI Search. First watch condition: Whether LangChain publishes measured search quality and latency across trace types, especially for behaviors whose evidence falls outside the retained 8K-token budget.

The release is a distinct analytical record because no prior New Runtime record was supplied; it documents a specific search interface and its stated implementation limits, without assuming a prior pattern record.

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`.

- topic hub: [Agent Observability](https://newruntime.com/topics/agent-observability.md): Explore the agent-observability topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- 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)