LangSmith by LangChain · Evals & Observability
11 companies with evidence on file — every claim below links to its source.
Monitors production traffic and runs Realm-X evals in CI.
Receipts · 2
“AppFolio used LangSmith to facilitate debugging during development and gain more insights” — blog.langchain.dev, Dec 16, 2024
“Evals are run in CI, with results tracked and integrated into PRs.” — blog.langchain.dev, Dec 16, 2024
Source last verified Sep 7, 2026 Full AppFolio stack →
Provides real-time observability and error tracking during testing.
Receipts · 1
“LangSmith was their first line of defense in the testing process” — blog.langchain.dev, Mar 10, 2025
Source last verified Jul 27, 2026 Full C.H. Robinson stack →
Self-hosted tracing and feedback loop for its Droid agents.
Receipts · 2
“Factory used LangSmith to automate their feedback loop and improve iteration speed by 2x” — blog.langchain.dev, Jun 19, 2024
“Factory used LangSmith to link feedback directly to each LLM call” — blog.langchain.dev, Jun 19, 2024
Source last verified Sep 7, 2026 Full Factory stack →
Provides tracing, evaluations, and prompt iteration for the AI Assistant.
Receipts · 2
“With LangSmith, Klarna could pinpoint what issues arose by seeing step-by-step how their AI assistant behaved.” — langchain.com, Feb 12, 2025
“adapting and improving evaluation tooling for LLM applications using LangSmith” — jobsinforex.com, Jul 21, 2026
Source last verified Jul 26, 2026 Full Klarna stack →
Drives a code-first evaluation strategy for AI agents.
Receipts · 1
“we utilized the LangSmith Vitest integration .” — blog.langchain.com, Feb 18, 2026
Source last verified Jul 27, 2026 Full monday.com stack →
Tests and monitors AI employee performance with traces and datasets.
Receipts · 1
“turned to LangSmith for LLM testing and observability.” — blog.langchain.dev, Aug 15, 2024
Source last verified Jul 27, 2026 Full Podium stack →
Monitors agent performance and distributes prompts across teams.
Receipts · 1
“LangSmith allows us to get things done scientifically.” — blog.langchain.dev, Feb 14, 2024
Source last verified Jul 27, 2026 Full Rakuten Group stack →
Runs a tailored evaluation framework over its multi-agent system.
Receipts · 1
“ServiceNow implemented a sophisticated evaluation framework in LangSmith tailored to their multi-agent system.” — blog.langchain.com, Nov 17, 2025
Source last verified Jul 27, 2026 Full ServiceNow stack →
Monitors agent performance and debugs workflows through experiments and traces.
Receipts · 1
“Trellix used LangSmith for experimentation and to action upon performance metrics.” — blog.langchain.dev, Apr 21, 2025
Source last verified Jul 27, 2026 Full Trellix stack →
Tracks LLM application lifecycle, debugging, and evaluation.
Receipts · 1
“With LangChain, LangGraph and LangSmith, Vodafone has successfully delivered advanced AI-driven solutions” — blog.langchain.dev, Mar 23, 2025
Source last verified Jul 27, 2026 Full Vodafone stack →
Traces, evaluates, and monitors its multi-stage LLM inference pipelines.
Receipts · 2
“LangSmith has been vital to understanding what’s happening in production and measuring experiment impact on key parameters.” — blog.langchain.dev, Jul 8, 2024
“Wordsmith has published a variety of evaluation sets for various tasks” — blog.langchain.dev, Jul 8, 2024
Source last verified Sep 7, 2026 Full Wordsmith stack →