TL;DR: We've added a tool to the Deep Agents SDK (Python) and CLI that allows models to compress their own context windows at opportune times.MotivationContext compression is an action that reduces the information in an agent’s working memory. Older messages are replaced by
By Vivek TrivedyTLDR: Agent = Model + Harness. Harness engineering is how we build systems around models to turn them into work engines. The model contains the intelligence and the harness makes that intelligence useful. We define what a harness is and derive the core components today's and tomor...
How Coding Agents Are Reshaping Engineering, Product and Design
EPD (Engineering, Product, and Design) at software company is about creating good software. Separate roles exist, but the end goal is functional software that solves a business problem that users can use. At the end of the day, this is just code. It is important to recognize that the output
By Robert XuRecently at LangChain we’ve been building skills to help coding agents like Codex, Claude Code, and Deep Agents CLI work with our ecosystem: namely, LangChain and LangSmith. This is not an effort unique to us - most (if not all) companies are exploring how to
We’re releasing a CLI along with our first set of skills to give AI coding agents expertise in the LangSmith ecosystem. This includes adding tracing to agents, understanding their execution, building test sets, and evaluating performance. On our eval set, this bumps Claude Code’s performance on
We’re releasing our first set of skills to give AI coding agents expertise in the open source LangChain ecosystem. This includes building agents with LangChain, LangGraph, and Deep Agents. On our eval set, this bumps Claude Code’s performance on these tasks from 29% to 95%.What
How Clay uses LangSmith to debug, evaluate, and monitor 300 million agents runs per month
Clay is the creative tool for growth — a platform where go-to-market teams build, enrich, and activate lists of companies and people. Sales teams use Clay to source target accounts, qualify leads with AI-powered research, draft personalized outreach, and route opportunities through their CRM. Clay's...
You don’t know what your agent will do until it’s in production
You can't monitor agents like traditional software. Inputs are infinite, behavior is non-deterministic, and quality lives in the conversations themselves. This article explains what to monitor, how to scale evaluation, and how production traces become the foundation for continuous improvement.
A key part of Agent Builder is its memory system. In this article we cover our rationale for prioritizing a memory system, technical details of how we built it, learnings from building the memory system, what the memory system enables, and discuss future work.
New in Agent Builder: all new agent chat, file uploads + tool registry
Today, we're expanding what you can do with LangSmith Agent Builder. It’s an big update built around a simple idea: working with an agent should feel like working with a teammate.We rebuilt Agent Builder around this idea. There is now an always available agent (”
TLDR: Our coding agent went from Top 30 to Top 5 on Terminal Bench 2.0. We only changed the harness. Here’s our approach to harness engineering (teaser: self-verification & tracing help a lot).The Goal of Harness EngineeringThe goal of a harness is to mold the
Clarifai 12.1: Building Production-Ready Agentic AI at Scale
Deploy production agentic AI with public MCP servers on Clarifai. Includes Artifacts for versioned pipeline storage and Pipeline UI improvements. Available in Public Preview.
Every time LLMs get better, the same question comes back: "Do you still need an agent framework?" It's a fair question. We've now built three generations of them, and each one looked different from the last. So here's what we believe:
Interrupt - The Agent Conference by LangChain - is where builders come to learn what's actually working in production. This year, we're bringing together more than 1,000 developers, product leaders, researchers, and founders to share what's coming next for agents—and how