<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/langsmith-engine-improves-agent-issue-detection-by-2x-vgllisrj4" -->

---
title: LangSmith Engine Improves Agent Issue Detection by 2x
description: LangSmith Engine, LangChain's in-platform agent for analyzing production agent traces, now identifies issues over 2x better on internal benchmarks and produces...
canonical: https://daily.dev/posts/langsmith-engine-improves-agent-issue-detection-by-2x-vgllisrj4
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: LangSmith Engine Improves Agent Issue Detection by 2x | daily.dev
og:description: LangSmith Engine, LangChain's in-platform agent for analyzing production agent traces, now identifies issues over 2x better on internal benchmarks and produces...
og:url: https://daily.dev/posts/langsmith-engine-improves-agent-issue-detection-by-2x-vgllisrj4
og:image: https://api.daily.dev/og/posts/VglliSRJ4.png
og:image:alt: LangSmith Engine Improves Agent Issue Detection by 2x
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# LangSmith Engine Improves Agent Issue Detection by 2x

**[LangChain](https://daily.dev/sources/langchain)** · 5 min read · 2 upvotes · 0 comments

## Summary

LangSmith Engine, LangChain's in-platform agent for analyzing production agent traces, now identifies issues over 2x better on internal benchmarks and produces fixes that score 25% better on Terminal-Bench, compared to its May launch. New features include self-hosted deployment support, Slack and Linear integrations for issue triage, a Reduced Analysis mode for cost control, automatic closing of stale issues, and tighter links to specific trace locations. Since launch, Engine has scanned over 60 million traces and surfaced more than 20,000 issues. Upcoming work focuses on automated verification of proposed fixes and auto-generated evaluation datasets. Available now for LangSmith Plus and Enterprise plans in SaaS and self-hosted deployments.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.langchain.com/blog/new-in-langsmith-engine-2x-better-issue-detection>

## Questions this post answers

### What new capabilities were added to LangSmith Engine for detecting production agent issues?

LangSmith Engine now performs over twice as well on internal benchmarks for identifying agent issues and 25% better on the Terminal-Bench industry benchmark for proposing fixes. New features include self-hosted deployment support, Slack alerts, Linear issue creation, a Reduced Analysis mode for cost control, automatic closing of stale issues, and stronger links to trace locations.

_daily.dev surfaces updates like these for engineers evaluating agent observability tooling._

### Can LangSmith Engine be used in a self-hosted LangSmith deployment?

Yes, Engine now supports self-hosted deployments. Its orchestration runs inside the customer's VPC while making requests to LangSmith Intelligence, a managed, zero data retention service, for inference powered by purpose-trained models, letting enterprises meet security and compliance requirements while still using Engine's automated issue detection.

_engineers weighing self-hosted versus SaaS agent tooling can track changes like this on daily.dev._

### How many traces has LangSmith Engine analyzed since launch and what has it found?

Since launching in May, LangSmith Engine has scanned over 60 million traces and identified more than 20,000 issues across customer agents, saving tens of thousands of hours of engineering work according to the vendor. Engine groups related occurrences and provides a diagnosis, evidence, and a proposed fix for each issue.

_teams scaling agent monitoring can follow adoption numbers like these on daily.dev._

## Similar posts on daily.dev

- [LangSmith is Now Available in Google Cloud Marketplace](https://daily.dev/posts/langsmith-is-now-available-in-google-cloud-marketplace-7bvguylu3) · LangChain · 3 upvotes · 0 comments
- [LangSmith Explained: Debugging and Evaluating LLM Agents](https://daily.dev/posts/langsmith-explained-debugging-and-evaluating-llm-agents-wy5ceqqjb) · DigitalOcean Community · 1 upvotes · 0 comments

---

Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#observability](https://daily.dev/tags/observability), [#langchain](https://daily.dev/tags/langchain), [#langsmith](https://daily.dev/tags/langsmith)

[View this post on daily.dev](https://daily.dev/posts/langsmith-engine-improves-agent-issue-detection-by-2x-vgllisrj4)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"LangSmith Engine Improves Agent Issue Detection by 2x","url":"https://daily.dev/posts/langsmith-engine-improves-agent-issue-detection-by-2x-vgllisrj4","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/langsmith-engine-improves-agent-issue-detection-by-2x-vgllisrj4"},"datePublished":"2026-08-25T17:58:00.347Z","dateModified":"2026-09-14T09:22:00.280Z","description":"LangSmith Engine, LangChain's in-platform agent for analyzing production agent traces, now identifies issues over 2x better on internal benchmarks and produces...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/47bae0ef1d81b5ce08b0b96da554863c?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/47bae0ef1d81b5ce08b0b96da554863c?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"LangChain","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"LangChain","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/0f4f2629e0724a849823f8cd0d913e13","url":"https://daily.dev/sources/langchain"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/langsmith-engine-improves-agent-issue-detection-by-2x-vgllisrj4","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,observability,langchain,langsmith","timeRequired":"PT5M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"LangChain","item":"https://daily.dev/sources/langchain"},{"@type":"ListItem","position":3,"name":"LangSmith Engine Improves Agent Issue Detection by 2x"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/langsmith-engine-improves-agent-issue-detection-by-2x-vgllisrj4#faq","mainEntity":[{"@type":"Question","name":"What new capabilities were added to LangSmith Engine for detecting production agent issues?","acceptedAnswer":{"@type":"Answer","text":"LangSmith Engine now performs over twice as well on internal benchmarks for identifying agent issues and 25% better on the Terminal-Bench industry benchmark for proposing fixes. New features include self-hosted deployment support, Slack alerts, Linear issue creation, a Reduced Analysis mode for cost control, automatic closing of stale issues, and stronger links to trace locations. daily.dev surfaces updates like these for engineers evaluating agent observability tooling."}},{"@type":"Question","name":"Can LangSmith Engine be used in a self-hosted LangSmith deployment?","acceptedAnswer":{"@type":"Answer","text":"Yes, Engine now supports self-hosted deployments. Its orchestration runs inside the customer's VPC while making requests to LangSmith Intelligence, a managed, zero data retention service, for inference powered by purpose-trained models, letting enterprises meet security and compliance requirements while still using Engine's automated issue detection. engineers weighing self-hosted versus SaaS agent tooling can track changes like this on daily.dev."}},{"@type":"Question","name":"How many traces has LangSmith Engine analyzed since launch and what has it found?","acceptedAnswer":{"@type":"Answer","text":"Since launching in May, LangSmith Engine has scanned over 60 million traces and identified more than 20,000 issues across customer agents, saving tens of thousands of hours of engineering work according to the vendor. Engine groups related occurrences and provides a diagnosis, evidence, and a proposed fix for each issue. teams scaling agent monitoring can follow adoption numbers like these on daily.dev."}}]}
```

