Changelog

Sign up for our newsletter to stay up to date

Powered by LaunchNotes

Loading...

December 2025

Pairwise annotation queues for comparing agent outputs

Pairwise Annotation Queues in LangSmith are a fast, structured way to compare two agent outputs side-by-side and pick a winner. Scoring subjective tasks is...

December 17, 2025

LangSmith Fetch: Debug agents from your terminal

We've launched LangSmith Fetch — a CLI tool that brings full LangSmith trace access directly into your terminal, coding environment, or IDE. If you build...

December 10, 2025

LangSmith Polly, our AI assistant for debugging, analyzing, and improving agents, is now in beta

We've launched Polly — an AI-powered assistant inside LangSmith that helps you debug, analyze, and improve your agents. Polly, now in beta, understands agent...

December 10, 2025

Unified cost tracking for LLMs, tools, retrieval

We’ve added full-stack cost tracking to LangSmith to make it easier to understand and monitor spend across complex agent applications. LangSmith now...

December 2, 2025

November 2025

Okta SCIM + SSO Integration

LangSmith is now live on the Okta Integration Network (OIN). Enterprise teams that use Okta can now: This makes it much simpler to centralize access...

November 17, 2025

October 2025

No Code Agent Builder in LangSmith, now in private preview

We're expanding who can build agents beyond developers with LangSmith Agent Builder— a no-code agent-building experience now in private preview. Build real...

October 29, 2025

Discover patterns in production traces with the Insights Agent

Traces contain valuable signal about an agent's capabilities and how users engage with it. Insights Agent helps you find signal into your traces by analyzing...

October 23, 2025

Evaluate end-to-end agent interactions with Multi-turn Evals

Today, we're launching Multi-turn Evals to help you measure how your agent is performing across an entire end-to-end interaction. Multi-turn evals are online...

October 23, 2025

Improved dataset creation: faster and more flexible

Uploading data from an existing CSV/JSONL files is one of the easiest ways to get started with datasets and experiments. We’ve revamped the upload flow to...

October 17, 2025

JavaScript Code Evals for faster eval workflows

JavaScript Code Evals allow you to write custom Code Evals in JavaScript in addition to Python. This gives you the flexibility to choose the language that...

October 7, 2025

Powered by LaunchNotes