The Most Common Questions About Agent Evals, Answered
Where to start with agent evals, offline vs online evals, evaluator types, LLM judges, benchmarks with Harbor, multi-turn evals, and keeping costs down.
LangChain Blog14 min read
LangSmith
73 stories
LangChain lets teams search AI-agent records for behavior, not just keywords
AI Search uses a model to check session records against plain-language questions. Its fixed reading budget favors conversations over tool output.
Superpower Daily3 min read
How Orange Business Built Live Intelligence with LangChain and LangSmith
Learn how Orange Business used LangChain and LangSmith to build Live Intelligence, a governed AI platform for agents, evals, observability, and production scale.
LangChain Blog5 min read
Open Models have crossed a threshold
Open models like GLM-5 and MiniMax M2.7 now match closed frontier models on core agent tasks — file operations, tool use, and instruction following — at a fraction of the cost and latency. Here's what our evals show and how to start using them in Deep Agents.
LangChain Blog7 min read
Open SWE: An Open-Source Framework for Internal Coding Agents
Built on Deep Agents and LangGraph, Open SWE provides the core architectural components for internal coding agents.
LangChain Blog9 min read
Deep Agents Deploy: an open alternative to Claude Managed Agents
Today we’re launching Deep Agents deploy in beta. Deep Agents deploy is the fastest way to deploy a model agnostic, open source agent harness in a production ready way.
LangChain Blog5 min read
Improving Deep Agents with harness engineering
Harness engineering improved LangChain's coding agent from Top 30 to Top 5 on Terminal Bench using self-verification, tracing, and context optimization.
LangChain Blog8 min read
The Roadmap to Mastering Agentic AI Systems in 2026
A four-level technical roadmap for building agentic AI systems, from single cognitive loops and stateful memory through multi-agent swarms and production observability.
KDnuggets10 min read
LangChain Explained in Telugu 🔥 | Build AI Agents from Scratch | LangGraph, RAG, MCP & LangSmith
ChatGPT answers questions… but how do we build AI systems that can actually complete tasks? What should I explain next — Comment below! 👇 In this video, we're exploring LangChain from scratch using one practical real-world example.
Withme Sravani
Search agent traces by behavior with AI Search in LangSmith
AI Search in LangSmith is a new way to query traces using natural language. Describe the behavior you're looking for, and LangSmith returns the traces where it happened.
LangChain Blog7 min read
Building Long-Running Agents with ScaleDown and Deep Agents
Use ScaleDown's constrained decoding models with LangChain and Deep Agents to summarize history, compress tool results, and extract data faster and cheaper.
LangChain Blog9 min read
AgentCore Pricing (Oct 2026): 12 Meters and 5 Alternatives
AgentCore pricing re-checked Oct 13, 2026: 12 meters, Runtime v1 at $0.0895 and v2 at $0.1276 per vCPU-hour, per-GB short-term memory, and 5 alternatives.
BetterClaw Blog18 min read
🔴 LangChain (LangSmith): Seeing some issues logging into the application
No — LangChain (LangSmith) is operational. Uptime: 99.98%. 3 incidents tracked (30d). Live status, updated every 5 minutes.
AIWatch Blog3 min read
AI agents can be unpredictable. Your control layer shouldn't be.
In multi-agent systems, agents can be individually correct and still produce a wrong result when they work together. One agent’s output becomes another agent’s context.
VentureBeat AI12 min read
How to build great out-of-the-box user experiences with Managed Deep Agents
Managed Deep Agents includes a new API for managing reactions for your distributed agents, and a system to dynamically assign emoji responses with your instrument of choice. Learn more.
LangChain Blog5 min read
How Snyk Turned an Internal Support Agent into a Customer Feature
Discover how Snyk transformed an internal support agent into Snyk Assist, a customer-facing AI feature powered by LangChain, LangGraph, and LangSmith.
LangChain Blog8 min read
Agents that can pay: building Restock with Stripe's Link and Managed Deep Agents
Build an agent that pays for real purchases. Restock runs in Slack on Managed Deep Agents and pays with Stripe's Link over the Machine Payments Protocol.
LangChain Blog6 min read
The share of enterprises trusting AI agents to make production changes on their own has fallen from 75% to 56%, VB Intelligence finds
Enterprises are increasingly hesitant to give AI agents carte blanche ability to deploy code or system changes to production without human approval, even as they continue investing in tools designed to evaluate agent reliability.Read more
VentureBeat AI12 min read
Showing 18 of 73 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts