← All sources

LangChain Blog news

The latest AI and developer news from LangChain Blog, with short summaries.

Visit website →

Prompt Caching with Deep Agents

·2026.06.27 02:00

June 2026: LangChain Newsletter — Fleet On-Call Copilot, Deep Agents Rubrics, and Other Updates

·1·2026.06.26 03:00

How SmithDB Builds Inverted Indexes for Full-Text Search

·2026.06.26 00:00

Why the Best AI Agents Should Be Simple: An Interview with Sierra's Zack Reneau-Wedeen

·2026.06.25 23:00

How Klarna's AI Assistant Redefined Large-Scale Customer Support for 85 Million Active Users

·2026.06.25 05:00

How to Meet EU AI Act Regulatory Requirements with LangSmith and LangChain OSS

·2026.06.25 05:00

How to Build Memory for AI Agents

·2026.06.25 01:00

How Factory Used LangSmith to Automate Feedback Loops and Double Iteration Speed

·2026.06.17 03:00

LangSmith: Product Homepage Redesign and Introduction of Tagging Feature for Resource Management

·2026.06.17 03:00

The Art of Loop Engineering

·2026.06.17 02:00

Why Fleet Offers Both General-Purpose Chat and Specialized Agents

·1·2026.06.17 00:00

Introducing Align Evals: Streamlining the LLM Application Evaluation Process

·1·2026.06.16 02:00

What Is an AI Agent?

·2026.06.16 02:00

Breaking Through LangSmith's Limits with Replit Agent's Complex Workflows

·2026.06.16 02:00

Building a Trace Judge with Fireworks That Cuts Costs by 100x

·2026.06.16 02:00

Agentic Engineering: How Swarms of AI Agents Are Redefining Software Engineering

·2026.06.16 01:00

Aligning LLM-as-a-Judge with Human Preferences

·2026.06.16 01:00

Agent Observability: How to Monitor and Evaluate LLM Agents in Production

·2026.06.16 01:00

How to Debug and Evaluate AI Agents Using Observability: A LangChain Guide

·2026.06.16 01:00

How LangChain Made Coding Agent Spending Predictable

·2026.06.16 00:00