We explore how increasing the number of instructions and tools available to a single ReAct agent affects its performance, benchmarking models like claude-3.5-sonnet, gpt-4o, o1, and o3-mini across two domains of tasks.

Vizient's GenAI platform helps users manage data to query for information ranging from patient outcomes to clinical benchmarking. See how they used LangGraph and LangSmith for multi-agent system reliability and prompt management.

See how Infor is using the full LangChain product suite — including LangChain, LangGraph, and LangSmith — to drive enterprise automation for the cloud.

LinkedIn, Uber, Replit, and Elastic are just a few of the companies using LangGraph for real use cases in production. Learn how they did it below!

Join us this May at Interrupt, LangChain’s inaugural conference where the future of AI agents takes center stage.

Have you ever wanted to take advantage of LangGraph's core features like human-in-the-loop, persistence/memory, and streaming without having to explicitly define a graph? We're excited to announce the release of the Functional API for LangGraph, available in Python and JavaScript. The functional API allows you

By Krish Maniar and William Fu-Hinthorn If you are interested in beta-testing more prompt optimization techniques, fill out interest form here. When we write prompts, we attempt to communicate our intent for LLMs to apply on messy data, but it's hard to effectively communicate every nuance in one

Introducing a new way to run evals using LangSmith’s Pytest and Vitest/Jest integrations.

Captide’s platform transforms how investment research teams work with financial data. By automating the extraction of insights and metrics from regulatory filings and investor relations documents, analysts can create customized datasets and analyses with extreme efficiency. At the heart of this innovation is their commitment to NLP workflows

In the thriving world of e-commerce, where customer satisfaction can make or break a brand, Minimal is leveraging the LangChain ecosystem to transform how support issues are handled. Minimal AI agents are delivering 80%+ efficiency gains over a broad variety of E-commerce stores while improving customer satisfaction. This year, Minimal

Most AI apps today follow a familiar chat pattern ("chat" UX). Though easy to implement, they create unnecessary interaction overhead, limit the ability of us humans to scale ourselves, and fail to use the full potential of LLMs. Over the past six months, we've been exploring

See how Acxiom debugged their agent application with LangSmith and built a scalable solution for their user base, complete with long-term memory, dynamic updates, and attribute-specific search.

LLMs are reaching a point of maturity where they are sufficiently capable of powering sophisticated AI agents. The agents they power are not free-range, pseudo-AGI-like agents, but rather vertical-specific agents addressing a specific use case, with a specific focus. Examples of these AI agents launched in the past year include

2024 was the year that agents started to work in production. Not the wide-ranging, fully autonomous agents that people imagined with AutoGPT. But more vertical, narrowly scoped, highly controllable agents with custom cognitive architectures. It's still not easy to build these agents - but it's entirely

Dive into LangSmith product usage patterns that show how the AI ecosystem and the way people are building LLM apps is evolving.