Blogsby GlyphAugust 2026: LangChain Newsletter, Managed Deep Agents, LLM Gateway, and More
Managed Deep Agents and LLM Gateway hit public beta, plus Deep Agents v0.7, Tuned Evaluators, Bring Your Own Cloud on AWS, and LangSmith Engine upgrades.
78 of 800 posts
Thu Aug 271 post
Wed Aug 2654 posts
Introducing Pytest and Vitest integrations for LangSmith Evaluations
Introducing a new way to run evals using LangSmith’s Pytest and Vitest/Jest integrations.
Role Based Access Control (RBAC) for LangSmith
LangSmith's Role Based Access Control (RBAC) helps enterprises manage resource access with custom roles and API keys.
LangServe Playground and Configurability
Deploy LangChain apps with LangServe's playground UI and configurable parameters. Experiment with models, share with teams, stream in real-time.
Cube x LangChain: Building AI experiences with LLMs and the semantic layer
Build AI-powered data experiences with Cube's semantic layer and LangChain. Prevent hallucinations, query in natural language, create conversational interfaces.
Using LangSmith to Support Fine-tuning
Learn how to fine-tune and evaluate LLMs with LangSmith for dataset management. Complete guide covers LLaMA2 and GPT-3.5 fine-tuning with practical examples.
Benchmarking Question/Answering Over CSV Data
Build better Q&A systems for CSV data using LangChain agents, retrieval, and LLM evaluation. Includes benchmarks, debugging insights, and open-source code.
Making Data Ingestion Production Ready: a LangChain-Powered Airbyte Destination
Scale retrieval apps to production with LangChain's Airbyte integration. Automate data ingestion with scheduling, text splitting, and 50+ embeddings.
Automating Web Research
Automate web research with LangChain's retriever. Run parallel searches, scrape pages, and synthesize information with LLMs, locally or in the cloud.
Plan-and-Execute Agents
Build reliable AI agents with Plan-and-Execute framework. Separate planning from execution for complex tasks with fewer errors.
Announcing our $10M seed round led by Benchmark
LangChain secures $10M seed round from Benchmark to empower developers building AI apps with our open-source framework for data-aware, agentic LLMs.
Retrieval
Build better AI apps with flexible retrieval methods in LangChain. Use any retriever, from semantic to hybrid, to create personalized ChatGPT for your data.
Timescale Vector x LangChain: Making PostgreSQL A Better Vector Database for AI Applications
Build faster AI apps with Timescale Vector for LangChain. Get 243% faster similarity search, time-based RAG, and PostgreSQL simplicity. Free 90-day trial.
Autonomous Agents & Agent Simulations
Explore how LangChain implements autonomous agents like AutoGPT and BabyAGI. Learn about planning techniques, memory systems, and agent simulations.
Meet Connery: An Open-Source Plugin Infrastructure for OpenGPTs and LLM apps
Discover Connery: open-source plugin infrastructure for LLM apps. Secure integrations, personalization, and human-in-the-loop control for AI agents.
LangChain State of AI 2023
Discover how developers build LLM applications in 2023. Insights on popular models, vectorstores, retrieval strategies, and testing methods from LangSmith.
OpenAI's Bet on a Cognitive Architecture
Why LangChain believes in open, customizable cognitive architectures over closed systems. Build reliable LLM agents with OpenGPTs and LangSmith.
How to design an Agent for Production
Build production-ready AI agents with LangChain. Technical guide covering OpenAI functions, tools, prompts, and architecture for Cal.ai's scheduling assistant.
Kay x Cybersyn x LangChain: Embedding SEC Filings for RAG
Retrieve context from SEC filings for RAG with Kay and Cybersyn's SEC Retriever on LangChain. Pre-embedded data, optimized retrieval, no setup required.
Eden AI x LangChain: Harnessing LLMs, Embeddings, and AI
Access multiple LLMs, embeddings, and AI tools through Eden AI's LangChain integration. Unified API for text generation, OCR, speech-to-text, and more.
Xata x LangChain: new vector store and memory store integrations
Integrate Xata with LangChain for vector and memory storage. Build AI apps with PostgreSQL-powered data, hybrid search, and chat history.
Introducing Airbyte sources within LangChain
Connect 300+ data sources to LangChain with Airbyte document loaders. Load from Stripe, Salesforce, Hubspot & more directly in Python.
Qdrant x LangChain: Endgame Performance
Qdrant and LangChain deliver production-ready RAG performance with async support, optimized resource usage, and scalable vector search for LLM apps.
Data-Driven Characters
Data-driven-characters is a repo for creating, debugging, and interacting your own chatbots conditioned on your own story corpora.
Auto-Evaluator Opportunities
Auto-evaluate LLM question-answer chains with LangChain's free tool. Generate test sets, grade answers, and optimize chain performance.
Applying OpenAI's RAG Strategies
Implement OpenAI's proven RAG strategies with LangChain. Explore query transformations, routing, post-processing, and evaluation methods for optimal retrieval.
Agent observability needs feedback to power learning
Traces show what an agent did; feedback shows what it meant. How explicit, implicit, LLM-as-judge and rule-based feedback turn observability into learning.
Building a company due diligence Agent with Deep Agents
A cookbook for automating company due diligence: Deep Agents orchestrates five research subagents and Parallel's Task API returns cited, sourced findings.
LangSmith Engine: How We Built an Agent for Improving Agents
A technical look at LangSmith Engine: how it analyzes traces at scale, turns recurring failures into actionable issues, and proposes evaluators and fixes.
EU Macroeconomic Analysis with Deep Agents and You.com
A Deep Agents research agent analyzes GDP across all 27 EU states, flags outliers like Ireland and Germany, and writes a cited briefing in about 45 minutes.
How Harmonic Rebuilt Scout on Deep Agents and 4x'd Retention
Harmonic rebuilt Scout on Deep Agents and LangSmith: iteration went from months to days, week-four retention rose 4x, and session duration increased 10x.
Build an Auditable VC Research Agent with Perplexity
Build a VC research agent that drafts a cited investment memo in about 90 seconds for $0.40, using the Perplexity Agent API, LangGraph, and LangSmith evals.
How Candidly Built State-Aware Agent Harnesses in LangSmith
Candidly's agent Cait reads partial traces to infer user state mid-conversation and steer replies, using a LangSmith labeling pipeline at 92.3% human agreement.
Wiki Memory: File-Based Memory for AI Agents
Wiki memory uses an agent to compress raw data into a persistent, file-based knowledge base. How it differs from RAG, real examples, and when to use it.
Proving Agentic AI ROI in Financial Services
How to prove agentic AI ROI in financial services: business KPIs, cost tracking and governance for RFP and AML use cases, using LangSmith and Pay-i together.
LangChain Announces Enterprise Agentic AI Platform Built with NVIDIA
Build, deploy, and monitor production-grade AI agents at scale with LangChain's enterprise agentic AI platform integrated with NVIDIA.
LangChain raises $125M to build the platform for agent engineering
We raised $125M at a $1.25B valuation to build the platform for agent engineering.
LangGraph Platform is now Generally Available: Deploy & manage long-running, stateful Agents
LangGraph Platform, our infrastructure for deploying and managing agents at scale, is now generally available. Learn how to deploy
AI Agent Latency 101: How do I speed up my AI agent?
Learn proven strategies to speed up your AI agent: reduce latency, optimize LLM calls, enable parallelism, and improve UX. Expert tips from LangChain.
LangChain and NVIDIA Launch NemoClaw Deep Agents Blueprint
LangChain and NVIDIA launch the NemoClaw Deep Agents blueprint, combining Deep Agents Code, Nemotron 3 Ultra, and OpenShell for open, governed enterprise agents.
Evaluating OpenWiki with WikiBench
We built WikiBench to test whether generated wikis help coding agents. Pairing a wiki with source code scored higher than source alone, at lower cost.
January 2026: LangChain Newsletter
Read about the latest product updates, events, and content from the LangChain team
Why We Rebuilt LangChain’s Chatbot and What We Learned
Learn how LangChain rebuilt their chatbot using Deep Agents and subgraphs for sub-15-second responses with precise citations, and what you can apply.
Reflections on Three Years of Building LangChain
Harrison Chase on LangChain's 3-year journey from open source to $1.25B company, announcing LangChain 1.0, LangSmith expansion, and $125M funding.
Introducing Interrupt: The AI Agent Conference by LangChain
Join us this May at Interrupt, LangChain’s inaugural conference where the future of AI agents takes center stage.
LangChain State of AI 2024 Report
Dive into LangSmith product usage patterns that show how the AI ecosystem and the way people are building LLM apps is evolving.
LangSmith: Redesigned product homepage and Resource Tags for better organization
LangSmith's homepage is now organized into Observability, Evaluation, and Prompt Engineering. Learn why we organized the homepage like this. Plus, see our latest Resource Tags updates.
LangChain's Second Birthday
Reflections on how LangChain has evolved, including our products, ecosystem, and community, over the past two years, and where we're headed next.
Pushing LangSmith to new limits with Replit Agent's complex workflows
See how Replit built their agents atop LangGraph and integrated LangSmith to pinpoint issues, improve the performance of their agents, and enable human-in-the-loop workflows.
How Podium optimized agent behavior and reduced engineering intervention by 90% with LangSmith
See how Podium tests across the lifecycle development of their AI employee agent, using LangSmith for dataset curation and finetuning. They improved agent F1 response quality to 98% and reduced the need for engineering intervention by 90%.
Announcing LangGraph v0.1 & LangGraph Cloud: Running agents at scale, reliably
Our new infrastructure for running agents at scale, LangGraph Cloud, is available in beta. We also have a new stable release of LangGraph.
Aligning LLM-as-a-Judge with Human Preferences
Deep dive into self-improving evaluators in LangSmith, motivated by the rise of LLM-as-a-Judge evaluators plus research on few-shot learning and aligning human preferences.
How Factory used LangSmith to automate their feedback loop and improve iteration speed by 2x
How Factory AI uses LangSmith to debug issues and close the product feedback loop, resulting in a 2x improvement in iteration speed.
How LangSmith and LangChain OSS Help You Meet EU AI Act Requirements
The EU AI Act compliance deadline is August 2, 2026. Learn what the EU AI Act requires, and how LangSmith and LangChain OSS products help you meet each requirement.
LangSmith LLM Gateway: Runtime Controls for Agents
LangSmith LLM Gateway is in public beta: spend caps, rate limits, model fallbacks and PII redaction for production agents, without provider lock-in.
Tue Aug 2516 posts
Debugging Deep Agents with LangSmith
Debug deep agents with LangSmith's tracing and analysis. Analyze complex traces, optimize prompts with Polly, and improve performance.
Using skills with Deep Agents
Learn how to use agent skills with Deep Agents CLI to build token-efficient AI agents. Discover, load, and execute skills dynamically.
The rise of "context engineering"
Learn context engineering: building dynamic systems that provide LLMs the right information, tools, and format to reliably accomplish tasks.
How Klarna's AI assistant redefined customer support at scale for 85 million active users
Klarna's AI assistant is revolutionizing the personal shopping experience, including customer service and productivity. See how they used LangGraph and LangSmith to achieve 80% faster customer resolution times.
Workspaces in LangSmith for improved collaboration and organization
Workspaces in LangSmith lets enterprises separate resources between different teams, business units, or deployment environments.
Multi-Vector Retriever for RAG on tables, text, and images
Learn how to implement multi-vector retriever for RAG across tables, text, and images. Explore cookbooks for semi-structured and multi-modal data retrieval.
Structured Tools
Build powerful LangChain agents with Structured Tools. Accept multiple inputs, create complex tool schemas, and unlock advanced AI agent capabilities.
LLMs and SQL
Query SQL databases using natural language with LLMs. Learn techniques to reduce hallucinations and build reliable text-to-SQL solutions with LangChain.
Multi-modal RAG on slide decks
Build multi-modal RAG apps for slide decks using GPT-4V. Compare approaches, evaluate with benchmarks, and deploy with LangChain templates for visual Q&A.
Agentic Engineering: How Swarms of AI Agents Are Redefining Software Engineering
Multi-agent systems that mirror real engineering teams, not just code faster, can cut debug time by 93% and compress cross-team delivery. Here's the architecture built on LangGraph.
How Lyft Built a Self-Serve AI Agent Platform with LangGraph and LangSmith
Lyft used LangGraph and LangSmith to build a self-serve AI agent platform for customer support, cutting agent development from months to weeks.
Introducing Rubrics: Build Agents that Evaluate and Correct Their Work
Deep Agents' RubricMiddleware adds a self-evaluation loop to your agent runs. Set a rubric, configure a grader, and get reliable outputs on tasks where correctness matters.
The Art of Loop Engineering
Agents automate real-world work, but reliable performance requires more than a good model, it requires a carefully designed harness built for specific tasks.
How We Build Agent Environments & Tasks
How we create synthetic agent environments and tasks: a spec generation step, a spec-to-task step, and a world spec that holds shared knowledge.
Building Self-Correcting Memory in OpenWiki
Learn how OpenWiki uses evidence-backed claims to detect stale knowledge, reduce hallucinations, and build self-correcting memory for evolving codebases.
LangSmith Engine Improves Agent Issue Detection by 2x
LangSmith Engine now detects agent issues over 2x better, proposes stronger fixes, supports Slack and Linear workflows, and is available for self-hosted deployments.
Mon Aug 242 posts
Building a 100x Cheaper Trace Judge with Fireworks
LangChain and Fireworks fine-tuned an open model to mine perceived error signals from production traces, matching frontier model performance at a fraction of the cost.
Toyota Scales Enterprise AI with Deep Agents and LangSmith
See how Toyota North America uses Deep Agents and LangSmith to run 50+ production agents, cut delivery from 6 months to 4 days, and track AI ROI.
Thu Aug 201 post
Test Agent Changes with LangSmith Preview Builds
Preview Builds let teams test pull request branches in temporary, production-like LangSmith deployments before merging agent changes.
Wed Aug 191 post
Introducing LangSmith Tuned Evaluators
LangSmith Tuned Evaluators attach quality feedback to production traces, starting with Perceived Error, to help teams find and fix agent mistakes.
Tue Aug 182 posts
Own Your Intelligence: The Key to Lasting AI Advantage
Learn why companies must own their agent systems, governance, context, and feedback loops to turn generic AI into lasting business advantage.
AgentCore Payments middleware for LangChain agents
Let your LangChain agents pay for APIs with deterministic session budgets. AgentCore Payments middleware signs x402 payments; LangSmith traces every one.
Sun Aug 161 post
What is an AI agent?
Learn what AI agents are, how they work in an LLM loop, and where workflows fit so you can build reliable, production-ready autonomous systems.