Agentic AI

Introducing Align Evals: Streamlining LLM Application Evaluation

LangChain has introduced **Align Evals**, a new feature within its **LangSmith** platform that helps developers calibra…

LangChain Launches Managed Deep Agents in Public Beta

LangChain has launched Managed Deep Agents in public beta, providing a dedicated environment for deploying autonomous A…

How LangChain Built an Autonomous AI Agent to Manage Kubernetes

LangChain recently published a detailed breakdown of how they built an autonomous Site Reliability Engineering (SRE) ag…

How to Evaluate AI Voice Agents Using LangSmith: A Practical Guide

LangChain recently detailed a practical framework for evaluating AI voice agents using LangSmith. Because voice agents…

How many of your agent's calls actually need a frontier model?

CX Agents Go Live: What Lyft, Vodafone, and LATAM Airlines Learned

LangChain has published a detailed account of how Lyft, Vodafone, and LATAM Airlines deployed Customer Experience (CX)…

Managed Deep Agents: the fastest way to ship a production deep agent

LangChain has introduced Managed Deep Agents, a managed service now in private beta that lets organisations run sophist…

Top AI Agent Platforms in Malaysia (2026): An Honest Comparison

Malaysian businesses are rapidly adopting autonomous AI agents in 2026, moving beyond basic chatbots to systems that ac…

Deep Agents vs LangChain vs LangGraph

LangChain has published a detailed comparison of three distinct approaches to building AI agents: Deep Agents, LangChai…

Stripe Built an AI Agent for 5,000 Staff in One Week. Here's What Malaysian Businesses Should Learn From It.

Stripe built Kai, a company-wide AI knowledge agent, in approximately one week using LangChain, LangGraph, and Deep Age…

How LangChain Built an Agent-First Data Stack

LangChain, the company behind one of the most widely used frameworks for building large language model (LLM) applicatio…

Own Your Intelligence: The Key to Lasting AI Advantage

LangChain's latest strategic brief argues that the companies who will win the AI race are not those who simply consume…

How Similarweb Evaluates Agent Reports with LangSmith

Similarweb, the digital intelligence company, has shared how it uses LangSmith — LangChain's evaluation and observabili…

Evaluating code review agents with ReviewBench

LangChain has introduced ReviewBench, a benchmarking framework designed to evaluate how well AI code review agents perf…

LangSmith LLM Gateway: runtime governance built into the agent lifecycle

LangChain has introduced the LangSmith LLM Gateway, a runtime governance layer built directly into its LangSmith platfo…

LangSmith LLM Gateway puts guardrails on autonomous AI agents — before they spend your budget

LangChain has introduced the LangSmith LLM Gateway, a runtime governance layer built directly into its LangSmith platfo…

Agentic AI Goes Mainstream: What Malaysian SMEs Need to Know

Agentic AI — software that plans and acts on multi-step goals with minimal human supervision — is shifting from pilots…