Introducing ambient agents Most AI apps today follow a familiar chat pattern ("chat" UX). Though easy to implement, they create unnecessary interaction overhead, limit the ability
Communication is all you need “What we’ve got here is failure to communicate” - Cool Hand Luke (1967) Communication is the hardest part of life. It’s also the
LangChain's Second Birthday Reflections on how LangChain has evolved — including our products, ecosystem, and community — over the past two years, and where we're headed next.
Memory for agents 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
Build stateful conversational AI agents with LangGraph and assistant-ui TL;DR: assistant-ui is an embeddable AI chat frontend for React applications. It supports streaming, generative UI, human-in-the-loop, and other UX paradigms crucial for agentic
UX for Agents, Part 3: Spreadsheet, Generative, and Collaborative UI/UX Learn about spreadsheet UX for batch agent workloads, Generative UI, and collaborative UX with agents.
UX for Agents, Part 2: Ambient 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.
UX for Agents, Part 1: Chat 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
Planning for Agents 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.
Why you should outsource your agentic infrastructure, but own your cognitive architecture In this third installment in our "In The Loop" series, learn why you should tailor your cognitive architecture to be application-specific, alongside running better infrastructure for your agentic apps.
What is a "cognitive architecture"? The second installment in our "In the Loop" series, focusing on what cognitive architecture means.
Aligning LLM-as-a-Judge with Human Preferences Deep dive into self-improving evaluators in LangSmith, motivated by the rise of LLM-as-a-Judge evaluators plus research on few-shot learning and aligning human preferences.
