See how Paradigm used LangSmith and LangChain to build, iterate, and monitor their AI agents.

For JavaScript developers - LangGraph v0.2, LangGraph Cloud, and LangGraph Studio are all available.

See how Podium tests across the lifecycle development of their AI employee agent, using LangSmith for dataset curation and finetuning. They improved agent F1 response quality to 98% and reduced the need for engineering intervention by 90%.

See the latest updates to the LangChain integration docs, including a new standardized format and improved API references that can help you find relevant information faster.

Learn about spreadsheet UX for batch agent workloads, Generative UI, and collaborative UX with agents.

LangGraph v0.2 includes new checkpointer libraries for increased customization — including a SQLite checkpointer for local workflows and an optimized Postgres checkpointer to take your app to production. Plus, learn about LangGraph Cloud in open beta.

With dynamic few-shot examples in LangSmith, you can Index examples in your datasets in one click and dynamically select the most relevant few-shot examples based on user input. This lets you rapidly iterate and improve LLM app performance.

This is our second post focused on UX for agents. We discuss ambient background agents, which can handle multiple tasks at the same time, and how they can be used in your workflow.

LangGraph Studio provides a specialized agent IDE for visualizing, interacting with, and debugging complex agentic applications. See how to use it on your desktop today.

Define and flexibly manage dataset schemas in LangSmith. Validate examples against a defined schema, and update the schema easily in the LangSmith UI.

At Sequoia’s AI Ascent conference in March, I talked about three limitations for agents: planning, UX, and memory. Check out that talk here. In this post I will dive deeper into UX for agents. Thanks to Nuno Campos, LangChain founding engineer for many of the original thoughts and

We ran a few experiments, which show how few-shot prompting can significantly enhance model accuracy - especially for complex tasks. Read on for how we did it (and the results).

See how an AI-powered employee for enterprise analytics used the LangSmith playground and debugging features to quickly identify LLM issues and to generate complex research reports.

The fourth installment in our "In the Loop Series," in which we talk about what planning means for an agent and how to improve it.

See our latest improvements to our core tool interfaces that make it turn any code into a tool, handle diverse inputs, enrich tool outputs, and handle tool errors effectively.