LangChain Blog - Plushcap

Blog URL

blog.langchain.dev

Posts YTD

171 ↑ vs 62 last year

Avg Posts/Month

10.2 since 2024

Monthly Post Volume

Start year: 2023 2024 2025 2026

Post Details

Search:

Title	Author	Published	Words	HN Pts
Why We Rebuilt LangChain’s Chatbot and What We Learned	--	2025-11-05	3,287	--
Agent Frameworks, Runtimes, and Harnesses- oh my!	--	2025-10-25	671	--
LangGraph 0.3 Release: Prebuilt Agents	--	2025-02-27	363	--
Is LangGraph Used In Production?	--	2025-02-04	795	--
Introducing Prompt Canvas: a Novel UX for Developing Prompts	--	2024-11-12	649	--
Ally Financial Collaborates with LangChain to Deliver Critical Coding Module to Mask …	--	2024-01-11	1,305	--
How to think about agent frameworks	--	2025-04-20	5,136	--
Promptim: an experimental library for prompt optimization	--	2024-11-13	885	--
Beyond RAG: Implementing Agent Search with LangGraph for Smarter Knowledge Retrieval	--	2025-02-22	2,561	--
Winning in AI means mastering the new stack	--	2024-02-16	2,016	--
Securing your agents with authentication and authorization	--	2025-10-13	1,557	--
Building LangGraph: Designing an Agent Runtime from first principles	--	2025-09-04	4,075	--
Introducing Align Evals: Streamlining LLM Application Evaluation	--	2025-07-29	594	--
Agent Protocol: Interoperability for LLM agents	--	2024-11-19	821	--
LangSmith for the full product lifecycle: How Wordsmith quickly builds, debugs, and …	--	2024-07-08	947	--
Enhancing RAG-based application accuracy by constructing and leveraging knowledge graphs	--	2024-03-15	1,769	--
Introducing DeepAgents CLI	--	2025-10-30	608	--
What is a "cognitive architecture"?	--	2024-07-05	751	--
LangFriend: a Journal with Long-Term Memory	--	2024-03-28	1,282	--
How C.H. Robinson is transforming the logistics industry with LangChain	--	2025-03-10	584	--
Reflection Agents	--	2024-02-21	1,295	--
The rise of "context engineering"	--	2025-06-23	1,367	--
LangGraph Studio: The first agent IDE	--	2024-08-01	896	--
LangGraph: Multi-Agent Workflows	--	2024-01-23	1,266	--
LangChain Partners with CommandBar on their Copilot User Assistant	--	2024-02-08	534	--
TAMM AI Assistant: Transforming Government Services in Abu Dhabi with LangChain and …	--	2025-04-15	834	--
How Outshift by Cisco achieved a 10x productivity boost with their Agentic …	--	2025-05-04	1,035	--
LangChain and LangGraph Agent Frameworks Reach v1.0 Milestones	--	2025-10-22	1,686	--
How to turn Claude Code into a domain specific coding agent	--	2025-09-11	2,256	--
Introducing the LangGraph Functional API	--	2025-01-29	1,708	--
Deep Agents	--	2025-07-30	774	--
LangGraph Platform in beta: New deployment options for scalable agent infrastructure	--	2024-10-31	941	--
Dataset schemas for fast and iterative data curation in LangSmith	--	2024-07-31	895	--
Improve agent quality with Insights Agent and Multi-turn Evals, now in LangSmith	--	2025-10-23	912	--
SCIPE - Systematic Chain Improvement and Problem Evaluation	--	2024-11-07	1,274	--
How Dataherald Makes Natural Language to SQL Easy	--	2024-02-14	748	--
Pairwise Evaluations with LangSmith	--	2024-05-15	965	--
Rakuten Group builds with LangChain and LangSmith to deliver premium products for …	--	2024-02-14	766	--
Catch production failures early with LangSmith Alerts	--	2025-04-22	455	--
UX for Agents, Part 3: Spreadsheet, Generative, and Collaborative UI/UX	--	2024-08-10	879	--
How Captide is redefining equity research with agentic workflows running on LangGraph …	--	2025-01-20	730	--
Workspaces in LangSmith for improved collaboration and organization	--	2024-06-13	779	--
Introducing OpenTelemetry support for LangSmith	--	2024-12-09	790	--
LangSmith: Redesigned product homepage and Resource Tags for better organization	--	2024-11-19	901	--
LangChain Integrates NVIDIA NIM for GPU-optimized LLM Inference in RAG	--	2024-03-18	868	--
Use Case Accelerant: Extraction Service	--	2024-03-06	1,882	--
Recap of Interrupt 2025: The AI Agent Conference by LangChain	--	2025-05-14	883	--
Documentation Refresh for LangChain v0.2	--	2024-05-20	711	--
Open Source Extraction Service	--	2024-03-26	1,426	--
BCG X Releases AgentKit, a Full-Stack Starter Kit for Building Constrained Agents	--	2024-02-12	1,125	--
Using Feedback to Improve Your Application: Self Learning GPTs	--	2024-03-20	1,139	--
LangChain v0.2: A Leap Towards Stability	--	2024-05-10	1,116	--
Monte Carlo: Building Data + AI Observability Agents with LangGraph and LangSmith	--	2025-09-10	831	--
How do I speed up my AI agent?	--	2025-03-15	995	--
Reflections on Three Years of Building LangChain	--	2025-10-20	1,617	--
Context Engineering	--	2025-07-02	2,640	--
LangGraph Platform is now Generally Available: Deploy & manage long-running, stateful Agents	--	2025-05-14	1,033	--
LangChain & LangGraph 1.0 alpha releases	--	2025-09-02	757	--
Regression Testing with LangSmith	--	2024-05-01	716	--
Custom Authentication and Access Control for LangGraph Platform	--	2024-12-19	756	--
Jockey: A Conversational Video Agent Powered by Twelve Labs APIs and LangGraph	--	2024-07-03	1,325	--
Introducing Assistant Editor for configuring agents in LangGraph Studio	--	2024-09-25	571	--
How DocentPro Built a Multi-Agent Travel Companion with LangGraph	--	2025-04-29	693	--
How Harmonic built an investment agent with LangGraph and LangSmith— so VCs …	--	2025-04-13	1,010	--
Why Definely chose LangGraph for building their multi-agent AI system	--	2025-04-07	678	--
Building a Data Visualization Agent with LangGraph Cloud	--	2024-09-12	4,474	--
LangSmith's Latest Feature: Grouped Monitoring Charts	--	2024-01-30	795	--
Tool Calling with LangChain	--	2024-04-11	1,511	--
How ServiceNow uses LangSmith to get visibility into its customer success agents	--	2025-11-17	1,018	--
Why do I need LangGraph Platform for agent deployment?	--	2025-05-22	950	--
Benchmarking Single Agent Performance	--	2025-02-10	2,902	--
LangChain raises $125M to build the platform for agent engineering	--	2025-10-20	719	--
Open Deep Research	--	2025-07-16	1,760	--
Introducing Open SWE: An Open-Source Asynchronous Coding Agent	--	2025-08-06	1,635	--
Announcing LangChain v0.3	--	2024-09-16	543	--
OpenRecovery: Transforming addiction recovery with LangGraph Platform	--	2024-10-03	708	--
How Build.inc used LangGraph to launch a Multi-Agent Architecture for automating critical …	--	2025-03-05	1,536	--
Multi Needle in a Haystack	--	2024-03-13	1,280	--
Launching Long-Term Memory Support in LangGraph	--	2024-10-08	516	--
LangChain's Second Birthday	--	2024-10-24	1,421	--
Command: A new tool for building multi-agent architectures in LangGraph	--	2024-12-10	517	--
Access Control Updates for LangSmith	--	2024-05-08	531	--
Composio’s SWE agent advances open-source on SweBench with a 48.6% score using …	--	2024-11-11	1,294	--
Why agent infrastructure matters	--	2025-07-27	968	--
Launching LangGraph Templates	--	2024-09-19	829	--
Empowering Development with FlowTestAI: Bridging APIs and LLMs for Enhanced Testing and …	--	2024-04-22	1,642	--
Doubling down on DeepAgents	--	2025-10-28	549	--
How Klarna's AI assistant redefined customer support at scale for 85 million …	--	2025-02-12	461	--
How Tradestack launched their MVP in 6 weeks using LangGraph Cloud	--	2024-09-25	973	--
How MUFG Bank increased sales efficiency by 10x with LangChain	--	2025-02-26	665	--
Meet Connery: An Open-Source Plugin Infrastructure for OpenGPTs and LLM apps	--	2024-02-07	1,838	--
LangChain v0.1.0	--	2024-01-08	2,726	--
Introducing LangSmith’s No Code Agent Builder	--	2025-10-29	937	--
Quickly Start Evaluating LLMs With OpenEvals	--	2025-02-26	844	--
Improving Memory Retrieval: How New Computer achieved 50% higher recall with LangSmith	--	2024-07-02	837	--
LangGraph Release Week Recap	--	2025-06-09	420	--
Human-in-the-loop with OpenGPTs and LangGraph	--	2024-02-08	671	--
How AppFolio transformed property management workflows with Realm-X, built using LangGraph and …	--	2024-12-16	890	--
How Chaos Labs built a multi-agent system for resolution in prediction markets	--	2024-11-06	892	--
How Rexera’s AI agents drive quality control with LangGraph	--	2024-10-09	955	--
Announcing LangGraph v0.1 & LangGraph Cloud: Running agents at scale, reliably	--	2024-06-27	1,294	--
How Cleric’s AI SRE leveled up with continuous learning through LangSmith	--	2024-12-02	838	--
Introducing ambient agents	--	2025-01-14	1,519	--
Build reliable agents in JavaScript with LangGraph.js v0.2: Now supporting Cloud and …	--	2024-09-03	894	--
LangSmith: Production Monitoring & Automations	--	2024-04-02	1,456	--
How Webtoon Entertainment built agentic workflows with LangGraph to scale story understanding	--	2025-05-19	890	--
Unify Launches Agents for Account Qualification using LangGraph and LangSmith	--	2024-10-08	1,450	--
UX for Agents, Part 2: Ambient	--	2024-08-02	959	--
Execute Code with Sandboxes for DeepAgents	--	2025-11-13	703	--
Build stateful conversational AI agents with LangGraph and assistant-ui	--	2024-09-11	925	--
LangChain State of AI 2024 Report	--	2024-12-19	1,161	--
How Bertelsmann Built a Multi-Agent System to Empower Creatives	--	2025-07-29	1,439	--
Acxiom's use of LangSmith for enhanced audience segmentation	--	2025-01-12	837	--
Rethinking Our Documentation	--	2024-04-05	1,036	--
Easier evaluations with LangSmith SDK v0.2	--	2024-12-05	954	--
Announcing LangSmith is now a transactable offering in the Azure Marketplace	--	2024-04-24	917	--
Benchmarking Multi-Agent Architectures	--	2025-06-10	1,711	--
How Dun & Bradstreet’s ChatD&B™ uses LangChain and LangSmith to deliver trusted, …	--	2024-11-18	954	--
Join LangChain at AWS re:Invent 2025	--	2025-11-10	513	--
Agent Middleware	--	2025-09-08	1,079	--
Benchmarking Query Analysis in High Cardinality Situations	--	2024-03-15	1,446	--
Improving core tool interfaces and docs in LangChain	--	2024-07-18	937	--
How Mendable leverages LangSmith to debug Tools & Actions	--	2024-01-25	1,288	--
Exploring Prompt Optimization	--	2025-01-28	3,849	--
How Minimal built a multi-agent customer support system with LangGraph & LangSmith	--	2025-01-20	807	--
Making it easier to build human-in-the-loop agents with interrupt	--	2024-12-14	872	--
LangGraph	--	2024-01-17	1,860	--
How Captide agents running on LangGraph Platform compress investment research from days …	--	2025-06-24	816	--
LangMem SDK for agent long-term memory	--	2025-02-18	1,457	--
Vodafone transforms data operations with AI using LangChain and LangGraph	--	2025-03-23	1,064	--
How to Build an Agent	--	2025-07-09	1,483	--
LangSmith and LangGraph Platform are now available in AWS Marketplace	--	2025-07-16	704	--
Introducing Interrupt: The AI Agent Conference by LangChain	--	2025-02-03	461	--
The Hidden Metric That Determines AI Product Success	--	2025-06-12	1,896	--
Dynamic few-shot examples with LangSmith datasets	--	2024-08-06	603	--
OpenGPTs	--	2024-01-31	1,612	--
Why you should outsource your agentic infrastructure, but own your cognitive architecture	--	2024-07-13	773	--
How to Build the Ultimate AI Automation with Multi-Agent Collaboration	--	2024-05-09	1,927	--
Self-Reflective RAG with LangGraph	--	2024-02-07	1,295	--
Memory for agents	--	2024-10-19	1,121	--
How Athena Intelligence optimized research reports with LangSmith, LangChain, and LangGraph	--	2024-07-21	902	--
JSON agents with Ollama & LangChain	--	2024-02-20	1,731	--
[Week of 7/8] LangChain Release Notes	--	2024-07-12	846	--
How We Deployed our Multi-Agent Flow to LangGraph Cloud	--	2024-07-15	1,178	--
How Vizient empowers healthcare providers with reliable GenAI insights using LangGraph and …	--	2025-02-10	537	--
Announcing the General Availability of LangSmith and Our Series A Led By …	--	2024-02-15	1,436	--
LangSmith Incident on May 1, 2025	--	2025-05-07	549	--
How Lovable uses LangSmith to debug & monitor agents in production	--	2025-03-25	422	--
Introducing End-to-End OpenTelemetry Support in LangSmith	--	2025-03-26	662	--
Semantic Search for LangGraph Memory	--	2024-12-05	734	--
Mental Health Therapy as an LLM State Machine	--	2024-01-26	1,457	--
Iterating Towards LLM Reliability with Evaluation Driven Development	--	2024-03-11	1,555	--
Pushing LangSmith to new limits with Replit Agent's complex workflows	--	2024-09-26	676	--
How Dosu Used LangSmith to Achieve a 30% Accuracy Improvement with No …	--	2024-05-02	1,605	--
Generating Usable Text with AI	--	2024-02-05	2,108	--
How and when to build multi-agent systems	--	2025-06-16	1,527	--
How Podium optimized agent behavior and reduced engineering intervention by 90% with …	--	2024-08-15	1,245	--
What is an AI agent?	--	2024-06-28	922	--
How Factory used LangSmith to automate their feedback loop and improve iteration …	--	2024-06-19	963	--
How Exa built a Web Research Multi-Agent System with LangGraph and LangSmith	--	2025-06-30	833	--
Graph-based metadata filtering for improving vector search in RAG applications	--	2024-04-25	2,586	--
Planning for Agents	--	2024-07-20	1,401	--
MCP: Flash in the Pan or Future Standard?	--	2025-03-08	1,366	--
Standard message content	--	2025-09-03	812	--
Introducing Pytest and Vitest integrations for LangSmith Evaluations	--	2025-01-22	1,280	--
Structured Report Generation Blueprint with NVIDIA AI	--	2025-01-06	697	--
Integrating LangChain with Azure Container Apps dynamic sessions	--	2024-05-16	703	--
LangGraph for Code Generation	--	2024-02-27	983	--
Communication is all you need	--	2024-10-26	1,754	--
Not Another Workflow Builder	--	2025-10-07	977	--
LangGraph v0.2: Increased customization with new checkpointer libraries	--	2024-08-07	1,036	--
UX for Agents, Part 1: Chat	--	2024-07-26	1,006	--
How Trellix cut log parsing time from days to minutes with LangGraph …	--	2025-04-21	1,031	--
How Infor is Transforming Enterprise AI using LangGraph and LangSmith	--	2025-02-05	904	--
Build and deploy a RAG app with Pinecone Serverless	--	2024-01-16	612	--
Plan-and-Execute Agents	--	2024-02-13	1,207	--
How Paradigm runs and monitors thousands of agents in parallel with LangChain …	--	2024-09-04	695	--
LangChain partners with Elastic to launch the Elastic AI Assistant	--	2024-01-30	887	--
Aligning LLM-as-a-Judge with Human Preferences	--	2024-06-26	1,256	--
Supercharging If-Statements With Prompt Classification Using Ollama and LangChain	--	2024-02-19	1,466	--
How Inconvo is improving customer-facing analytics with conversational AI built on LangGraph	--	2025-03-19	493	--
Top 5 LangGraph Agents in Production 2024	--	2024-12-31	657	--
LangChain Integration Docs: Find information faster with revamped pages & API references	--	2024-08-14	538	--
How Jimdo empower solopreneurs with AI-powered business assistance	--	2025-11-19	990	--
Using skills with Deep Agents	--	2025-11-25	565	--
How agents can use filesystems for context engineering	--	2025-11-21	1,655	--
How Airtop built web-automation for AI agents powered by the LangChain ecosystem	--	2024-11-26	670	--
LangSmith Agent Builder now in Public Beta	--	2025-12-02	1,521	--
Evaluating Deep Agents: Our Learnings	--	2025-12-03	1,661	--
Evaluating DeepAgents CLI on Terminal Bench 2.0	--	2025-12-05	763	--
Introducing Polly: Your AI Agent Engineer	--	2025-12-10	808	--
Agent Engineering: A New Discipline	--	2025-12-09	1,271	--
Introducing LangSmith Fetch: Debug agents from your terminal	--	2025-12-10	953	--
Debugging Deep Agents with LangSmith	--	2025-12-10	1,196	--
Fastweb + Vodafone: Transforming Customer Experience with AI Agents using LangGraph and …	--	2025-12-16	1,545	--
In software, the code documents the app. In AI, the traces do.	--	2026-01-10	1,409	--
Building Multi-Agent Applications with Deep Agents	--	2026-01-21	1,104	--
Deploy agents instantly with Agent Builder templates	--	2026-01-21	660	--
From Traces to Insights: Understanding Agent Behavior at Scale	--	2026-01-20	1,179	--
Choosing the Right Multi-Agent Architecture	--	2026-01-14	1,578	--
January 2026: LangChain Newsletter	--	2026-01-29	879	--
Context Management for Deep Agents	--	2026-01-28	1,182	--
How Remote uses LangChain and LangGraph to onboard thousands of customers with …	--	2026-01-19	1,138	--
Now GA: LangSmith Agent Builder	--	2026-01-13	485	--
LangSmith is Now Available in Google Cloud Marketplace	--	2026-02-09	766	--
The two patterns by which agents connect sandboxes	--	2026-02-10	1,389	--
On Agent Frameworks and Agent Observability	--	2026-02-12	981	--
Join us for Interrupt: The Agent Conference	--	2026-02-12	289	--
Improving Deep Agents with harness engineering	--	2026-02-17	1,762	--
monday Service + LangSmith: Building a Code-First Evaluation Strategy from Day 1	--	2026-02-18	1,826	--
New in Agent Builder: all new agent chat, file uploads + tool …	--	2026-02-18	965	--
How to Use Memory in Agent Builder	--	2026-02-19	934	--
How we built Agent Builder’s memory system	--	2026-02-21	2,107	--
Agent Observability Powers Agent Evaluation	--	2026-02-21	3,097	--
You don’t know what your agent will do until it’s in production	--	2026-02-25	2,772	--
How Clay uses LangSmith to debug, evaluate, and monitor 300 million agents …	--	2026-03-01	1,434	--
LangSmith CLI & Skills	--	2026-03-04	581	--
LangChain Skills	--	2026-03-04	425	--
Evaluating Skills	--	2026-03-05	1,798	--
How we built LangChain’s GTM Agent	--	2026-03-09	2,192	--
How Coding Agents Are Reshaping Engineering, Product and Design	--	2026-03-10	1,992	--
Autonomous context compression	--	2026-03-11	845	--
Febraury 2026: LangChain Newsletter	--	2026-03-03	929	--
Introducing deploy cli	--	2026-03-16	268	--
LangChain Announces Enterprise Agentic AI Platform Built with NVIDIA	--	2026-03-16	1,205	--
Open SWE: An Open-Source Framework for Internal Coding Agents	--	2026-03-17	1,859	--
Introducing LangSmith Sandboxes: Secure Code Execution for Agents	--	2026-03-17	855	--
Polly is generally available everywhere you work in LangSmith	--	2026-03-18	693	--
Introducing LangSmith Fleet	--	2026-03-19	1,104	--
Organizing Context in a Multi-Agent Harness	Thushanth Bengre, Chester Curme	2026-09-08	1,278	--
Two different types of agent authorization	--	2026-03-23	858	--
How Moda Builds Production-Grade AI Design Agents with Deep Agents	--	2026-03-24	1,339	--
Join LangChain at Google Cloud Next 2026	--	2026-03-23	728	--
Skills in LangSmith Fleet	--	2026-03-25	743	--
How Middleware Lets You Customize Your Agent Harness	--	2026-03-26	1,188	--
How Kensho built a multi-agent framework with LangGraph to solve trusted financial …	--	2026-03-26	984	--
How we build evals for Deep Agents	--	2026-03-26	1,910	--
Agent Evaluation Readiness Checklist	--	2026-03-27	4,209	--
Announcing the LangChain + MongoDB Partnership: The AI Agent Stack That Runs …	--	2026-03-31	1,228	--
March 2026: LangChain Newsletter	--	2026-04-01	935	--
Open Models have crossed a threshold	--	2026-04-02	1,457	--
How My Agents Self-Heal in Production	--	2026-04-03	1,332	--
Continual learning for AI agents	--	2026-04-05	928	--
Deep Agents v0.5	--	2026-04-07	964	--
Arcade.dev tools now in LangSmith Fleet	--	2026-04-07	663	--
Better Harness: A Recipe for Harness Hill-Climbing with Evals	--	2026-04-08	2,059	--
Previewing Interrupt 2026: Agents at Enterprise Scale	--	2026-04-09	844	--
Human judgment in the agent improvement loop	--	2026-04-09	2,671	--
Deep Agents Deploy: an open alternative to Claude Managed Agents	--	2026-04-09	1,033	--
Your harness, your memory	--	2026-04-11	1,582	--
Reusable Evaluators and Evaluator Templates in LangSmith	Catherine Qiao Jacob Talbot April 16, 2026 2 min	2026-04-16	960	--
A Developer’s First 10 Minutes: Secure LangChain Agents with Cisco AI Defense	Siddhant Dash April 16, 2026 X min	2026-04-16	878	--
Agentic Engineering: How Swarms of AI Agents Are Redefining Software Engineering	Renuka Kumar Prashanth Ramagopal April 17, 2026 X min	2026-04-17	2,402	--
How We Made Our Docs Test Themselves	Naomi Pentrel April 15, 2026 X min	2026-04-15	924	--
How Credit Genie used Insights Agent to improve their AI financial assistant	David Li Jeffrey Ngai Goyo Lozano Palacio Charles Yuan April 20, 2026 X min	2026-04-20	1,176	--
The Runtime Behind Production Deep Agents	Sydney Runkle Vivek Trivedy April 20, 2026 24 min	2026-04-20	4,928	--
How LangSmith and LangChain OSS Help You Meet EU AI Act Requirements	Jacob Talbot Becca Weng April 27, 2026 7 min	2026-04-27	1,358	--
April 2026: LangChain Newsletter	The LangChain Team April 27, 2026 4 min	2026-04-27	860	--
The Agent Improvement Loop Starts with a Trace	Sam Crowder March 31, 2026 12 min	2026-03-31	2,545	--
How we built Agent Builder’s memory \| Building memory into your agents	Harrison Chase January 16, 2026 11 min	2026-01-16	2,286	--
Running Subagents in the Background	Hunter Lovell Colin Francis April 16, 2026 4 min	2026-04-16	1,522	--
How Madrigal Built a Flexible and Scalable Multi-Agent Research and Intelligence Platform …	Parth Patel Ron Filippo April 29, 2026 11 min	2026-04-29	2,497	--
Interrupt Preview: Meet the MC	Becca Weng April 28, 2026 7 min	2026-04-28	1,390	--
Tuning Deep Agents to Work Well with Different Models	Vivek Trivedy Mason Daugherty April 29, 2026 5 min	2026-04-29	1,135	--
Agent observability needs feedback to power learning	Harrison Chase	2026-05-05	1,450	--
Building a company due diligence agent with Deep Agents, LangSmith and Parallel	Matt Harris, Nick Martitsch, Srimanth Tangedipalli, Karan Singh	2026-05-08	2,483	--
LangSmith LLM Gateway: runtime governance built into the agent lifecycle	Martha Janicki	2026-05-13	1,090	--
Introducing LangSmith Context Hub	Harrison Chase	2026-05-13	1,878	--
New in Deep Agents v0.6	Sydney Runkle	2026-05-13	2,199	--
Introducing LangSmith Engine	Ben Tannyhill	2026-05-13	973	--
The Agent Development Lifecycle	Harrison Chase	2026-05-09	2,714	--
LangSmith Sandboxes are Generally Available	Mukhil Loganathan	2026-05-13	1,046	--
Introducing Managed Deep Agents	Victor Moreira	2026-05-13	973	--
Introducing LangChain Labs	Harrison Chase	2026-05-14	550	--
Everything we shipped at Interrupt	Jacob Talbot	2026-05-14	2,154	--
Delta Channels: Evolving our Runtime for Long-Running Agents	Sydney Runkle	2026-05-12	1,350	--
Give Your Agents an Interpreter	Hunter Lovell	2026-05-20	2,419	--
How We Built LangSmith Engine, Our Agent for Improving Agents	Palash Shah	2026-05-19	3,390	--
How Auth Proxy secures network access for LangSmith agent sandboxes	Mukil Loganathan	2026-05-21	1,636	--
From Token Streams to Agent Streams	Christian Bromann, Nick Hollon	2026-05-21	1,918	--
Mission Control: Operating Self-Hosted LangSmith on Kubernetes	Gethin Dibben	2026-05-26	1,053	--
May 2026: LangChain Newsletter	The LangChain Team	2026-05-27	589	--
How Lyft Built a Self-Serve AI Agent Platform for Customer Support with …	Akshay Sharma	2026-05-27	1,948	--
The Anatomy of an Agent Harness	--	2026-03-10	2,279	2
Building workflows for agents with Skills and Interpreters	Hunter Lovell	2026-05-29	2,696	--
EU macroeconomic analysis with Deep Agents, LangSmith, and the You.com Finance Research …	Srimanth Tangedipalli, Karan Singh, Saurabh Sharma, Akhil Pothana	2026-05-20	4,101	--
How Rippling Went AI-Native Across Every Product in 6 Months with Deep …	Sofia Sulikowski	2026-06-01	1,139	--
Introducing Rubrics: Build Agents that Evaluate and Correct Their Work	Shrikar Seshadri, Sydney Runkle	2026-06-02	837	--
Designing Efficient Verifiers for Legal Agents	LangChain Labs, Harvey	2026-06-02	1,324	--
How Harmonic Rebuilt Scout on Deep Agents and 4x'd Retention with LangSmith	Sofia Sulikowski	2026-06-03	1,503	--
How to Build a Custom Agent Harness	Sydney Runkle	2026-06-03	1,073	--
Fault Tolerance in LangGraph: Retries, Timeouts, and Error Handlers	Quanzheng Long, Sydney Runkle	2026-06-04	1,782	--
Why Model Neutrality Matters More Than Cloud Neutrality	Neil Dahlke	2026-06-04	1,216	--
Give your agent its own computer	Amy Ru	2026-06-05	1,374	1
The Missing Link Between Agents and Applications	Christian Bromann	2026-06-10	1,214	1
Full Text Search in SmithDB: Designing an Inverted Index for Object Storage	Ankush Gola, Akshay Aurora, Sumedh Arani	2026-06-10	3,055	--
How Benchling builds agents when the smartest AI isn't smart enough	James Donner	2026-06-11	675	--
Building a 100x Cheaper Trace Judge with Fireworks	LangChain Labs, Fireworks	2026-06-15	1,326	--
How to Choose the Right Sandbox for Your Agent	Rahul Verma	2026-06-12	1,166	--
Building Box AI: How an Enterprise Content Platform Went AI-Native with Deep …	Sofia Sulikowski	2026-06-12	1,080	--
How We Made Coding Agent Spend Predictable	Martha Janicki	2026-06-15	924	--
Why Fleet Has Both General Purpose Chat and Specialized Agents	Brace Sproul	2026-06-16	1,327	--
The Art of Loop Engineering	Sydney Runkle	2026-06-16	1,234	2
How To Give Your Agent Memory	Jake Broekhuizen	2026-06-24	1,168	--
Prompt Caching with Deep Agents	Alex Olsen	2026-06-26	1,006	--
Full Text Search in SmithDB: Constructing and Querying our Inverted Index (Pt. …	Ankush Gola, Akshay Aurora, Sumedh Arani	2026-06-25	2,118	--
Why the best agents are simpler than you think	James Donner	2026-06-25	761	--
June 2026: LangChain Newsletter	The LangChain Team	2026-06-25	656	--
Introducing Dynamic Subagents in Deep Agents	Sydney Runkle, Colin Francis, Hunter Lovell	2026-06-29	1,795	--
How Candidly Built State-Aware Agent Harnesses with LangSmith	Ben Levine, Patrick Hendershott	2026-06-29	2,418	--
How to Use RLMs in Deep Agents	Sydney Runkle	2026-07-01	1,534	--
Running Untrusted Agent Code Without a Sandbox	Hunter Lovell	2026-06-30	1,037	--
Wiki Memory	Harrison Chase	2026-06-30	654	--
Harbor x LangChain: A Unified Stack for Evaluating Agents	Nicholas Bohm, Nick Hollon	2026-06-30	1,307	--
How Pendo used LangSmith to trace Novus from user behavior to code …	Zain Lakhani	2026-07-01	1,082	--
Introducing OpenWiki, an open source agent for repo documentation	Brace Sproul	2026-07-01	728	--
Your coding agent bill doubled. Here’s how to fix it.	Amy Ru	2026-07-02	1,127	--
Tuning the harness, not the model: a Nemotron 3 Ultra playbook	Nick Hollon, Srimanth Tangedipalli	2026-07-08	2,215	3
LangChain and NVIDIA launch the NemoClaw Deep Agents Blueprint	The LangChain Team	2026-07-08	1,206	--
Improving Agents is a Data Mining Problem	Vivek Trivedy	2026-07-07	1,399	--
Deep Agents Code on NemoClaw: a governed blueprint for your most sensitive …	Srimanth Tangedipalli	2026-07-08	1,332	--
How Schneider Electric Built Their LLMOps Foundations At Enterprise Scale With LangSmith	Yoann Bersihand, Nicolas Gauthier, Amaury Gelin	2026-07-07	1,978	--
Introducing OpenWiki Brains, general-purpose wiki memory for agents	Brace Sproul	2026-07-10	1,269	--
Building an auditable VC research agent with the Perplexity Agent API and …	Srimanth Tangedipalli, Karan Singh, Ryan Buchmayer	2026-06-26	991	--
Your coding agents are a black box. Here's how to crack them …	Hari Harish	2026-07-14	894	--
New in LangSmith Fleet: Bring agents into Slack in one click	Caspar Broekhuizen	2026-07-15	730	--
Agents need their own computer. Here's how to give them one safely.	Amy Ru	2026-07-15	2,393	--
OpenWiki 0.2 is adopting the OKF support	Brace Sproul	2026-07-16	744	--
Proving the ROI of agentic AI in financial services	Karan Singh, David Tepper	2026-07-17	2,663	--
Building Governed Agents: A Framework for Cost, Control, and Compliance	Martha Janicki	2026-07-20	2,886	--
IssueBench - How We Evaluate Engine	Nick Bray, Arjun Nargolwala	2026-07-20	1,094	--
Trace voice agents in LangSmith	Caroline di Vittorio	2026-07-21	646	--
How Apollo Rebuilt Its AI Assistant on Deep Agents to Power the …	Sofia Sulikowski	2026-07-21	1,140	--
How We Benchmark Deep Agents	Nick Hollon, Harrison Chase	2026-07-23	712	--
Towards Automating Eval Engineering	Vivek Trivedy	2026-07-22	943	--
July 2026: LangChain Newsletter	The LangChain Team	2026-07-23	623	--
3 Years of Graph Engineering with LangGraph	Sydney Runkle, Harrison Chase	2026-07-22	1,256	--
What does it mean to "own your intelligence"?	Harrison Chase	2026-07-25	1,624	--
Deep Agents v0.7	Sydney Runkle	2026-07-29	1,230	--
LangSmith LLM Gateway: runtime controls for production agents	Martha Janicki, Ramon Petgrave	2026-07-30	1,214	--
How we built LangChain’s agent-first data stack	Emily Hawkins	2026-07-28	2,731	--
How Similarweb Evaluates Long-Form Agent Research Reports with LangSmith	Liora Korni	2026-07-29	2,096	--
Evaluating code review agents with ReviewBench	Nick Hollon	2026-07-31	1,178	--
How Stripe Built Kai, its Company-Wide AI Agent, on Deep Agents	Sofia Sulikowski	2026-08-03	1,881	--
Customer Experience (CX) Agents in Production: Lessons from Lyft, Vodafone, and LATAM …	Jess Ou	2026-08-04	4,746	--
How to evaluate voice agents: execution, outcomes, and experience	Caroline di Vittorio	2026-08-04	2,087	--
How we build an autonomous SRE Agent for Kubernetes Deployments	Eric Johanson	2026-08-05	1,689	1
Deep Agents vs LangChain vs LangGraph	Sydney Runkle	2026-08-06	1,627	--
Building monday.com Sidekick: why capable agents need more than just tools	Omri Bruchim	2026-08-11	2,690	--
How many of your agent's calls actually need a frontier model?	Srimanth Tangedipalli, Karan Singh	2026-08-11	2,404	--
Why managed agents are the next big thing in agent building	Harrison Chase	2026-08-12	1,154	--
LangSmith BYOC is now generally available on AWS	Romain Priour	2026-08-12	1,279	--
Introducing LangSmith Tuned Evaluators, starting with Perceived Error	Jake Broekhuizen, Shamik Karkhanis, Vivek Trivedy	2026-08-18	827	--
Agentic Commerce at Scale: Your LangChain agents can transact securely	Srimanth Tangedipalli, Karan Singh, Nneoma Okoroafor, Madhu Samhitha Vangara, Chethan Shriyan, WenChaun Lee	2026-08-17	1,959	--
LangSmith Preview Builds: Test agent changes before production	Victor Moreira	2026-08-20	750	--
How Toyota North America Put Enterprise AI on the Balance Sheet with …	Sofia Sulikowski	2026-08-24	1,133	--
Building Self-Correcting Memory in OpenWiki	Colin Francis	2026-08-25	1,412	--
New in LangSmith Engine: >2x better issue detection	Trammell Saltzgaber, Ben Tannyhill	2026-08-25	862	--
How We Build Agent Environments & Tasks	Vivek Trivedy, Nick Hollon	2026-08-25	2,220	--
August 2026: LangChain Newsletter	The LangChain Team	2026-08-26	662	--
Evaluating OpenWiki with WikiBench	Nick Hollon	2026-08-26	1,077	--
Scaling Agents in Europe & The Middle East: Lessons from Schneider Electric, …	Jess Ou	2026-09-03	3,319	--
Agents That Pay \| How Nevermined Empowers LangChain Agents to Buy and …	Josh Wadinski, Rodolphe Marques, Karan Singh	2026-09-03	2,371	--
MCP in LangChain: Stateless Protocol, Elicitation, and More!	Sydney Runkle	2026-09-03	1,216	--
We built SmithDB, the data layer for agent observability	Ankush Gola	2026-05-13	2,054	3
Managed Deep Agents is now in Public Beta	Victor Moreira	2026-08-07	1,940	2

Plushcap, by Matt Makai. 2021-2026.