David Duong

☕️ Building agents in Java or Go? We want to hear from you! Join the waitlist to get early access and help shape the future of LangGraph in your language. Sign up ➡️ airtable.com/appeUtF0AROUCZ…

Building Better Coding Agent Harnesses at @LangChain we're thinking hard about the science of harness engineering + open research on what works & doesn't A quick peak on our deepagents X Terminal Bench 2.0 work, shoutout to @alexgshaw & Harbor (they're great). Broad research goals: 1. Find general purpose agent improvement recipes 2. Measure which design changes most affect model performance and how 3. Measure if/how models are non-fungible in their harness Some previews on what worked well: - Self-Verification & Iteration as first class citizens. Models are very good at self correction if they get a feedback signal, but they often won't participate in this loop. So designing prompts & deterministic hooks to force them into this helps a lot. - Automated Context Engineering: Pre-fetching some environment context up front avoids discovery errors for tools/files. - Large scale reflection over Traces is a powerful general recipe for stratifying errors + validating proposed improvements We'll be releasing a blog and research artifacts soon on all of this! Will return to measure more vectors of harness design + use codex-5.3 If you're interested in effective harness engineering and building great coding agents, would love to hear from you

🎉📅 Interrupt 2026 — the AI Agent Conference by LangChain — is back May 13-14 in SF 1,000+ practitioners. Production agents. Real world lessons. Why you should come: → Hear from teams scaling agents in production → Get hands-on in workshops with the LangChain team → See new product drops first → Connect with builders solving the same challenges you are 🎟️ Tickets drop Feb 12 — seats are limited Sign up to get notified: interrupt.langchain.com/?utm_medium=so…

We surveyed 1,300+ developers and business leaders to understand how AI agents are actually being built, tested, and shipped to real users. What are the most popular agent use cases? Biggest challenges when building agents? And who's really using observability or evals tooling? Read the full report here ➡️ bit.ly/state-of-agent… Here's 6 key insights below 🧵👇

@Yashika_dev @langchain Optimized fetch output! Raw JSON / YAML is too noisy for LLMs

@langchain Real Q: Is fetch output optimized for agent context windows (like Cursor) or is it just raw JSON ? Piping full traces usually = instant token overflow Curious if the CLI formats it to actually fit the token budget

Today, we’re shipping new ways to observe, analyze, and debug agents with LangSmith: • Polly: an AI assistant for AI engineering that helps you understand traces, threads, and improve prompts • LangSmith Fetch: a CLI for pulling trace & thread data straight into your terminal or coding agent Agents are running longer and getting more complex, which demands new debugging workflows beyond simple LLM apps. We wrote a blog on the trends behind this shift— and why tools like Polly and LangSmith Fetch are needed. Shipping reliable agents requires full visibility into agent behavior, with tooling that helps you reason over that data in the UI, the terminal, or alongside coding agents. 📔Learn more about Polly: blog.langchain.com/introducing-po… 📔Learn more about LangSmith Fetch: blog.langchain.com/introducing-la… 📔How to observe deep agents: blog.langchain.com/debugging-deep… 📽️ Polly video tutorial: youtube.com/watch?v=4Ox2gd… 📽️ LangSmith Fetch video tutorial: youtube.com/watch?v=e_G_rX…

An agent for your agents 🔄

What a night! ⚡️ Huge thanks to everyone who joined @langchain x @Dynatrace AI Agent Night in Berlin 🇩🇪 — amazing energy and inspiring conversations around AI agents. Big shout-out to @Dynatrace for co-hosting and to @thisthatdc for an awesome talk on OpenTelemetry for GenAI — instrumenting and monitoring agentic AI like a pro. 🙌 Until next time! 💫 #LangChain #AIagents #BerlinTech

🥳Announcing LangChain and LangGraph 1.0 LangChain and LangGraph 1.0 versions are now LIVE!!!! For both Python and TypeScript Some exciting highlights: - NEW DOCS!!!! - LangChain Agent: revamped and more flexible with middleware - LangGraph 1.0: we've been really happy with LangGraph and this is our official stamp of approval - Standard content blocks: swap seamlessly between models Read more about it here: blog.langchain.com/langchain-lang… We hope you love it!

So proud to share LangChain and LangGraph 1.0 with you all! 🥳 We've packed in so many improvements - a new agent builder, flexible agent middleware, provider agnostic content blocks, and beautiful new docs. ✨ Loved diving into the technical details in the blog post and joining my fellow OSS devs @huntlovell and @WHinthorn in a roundtable led by @hwchase17 to walk through the evolution of LangChain OSS! 🎥

@hwchase17 Amazing work on getting LangChain and LangGraph to 1.0!

@hwchase17 Let's go! 🫡

It's been a journey!

We raised $125M to build the platform for agent engineering. Thank you to our investors (@IVP, @sequoia, @benchmark, @AmplifyPartners, @SapphireVC, @CapitalG, and more) for their belief in us, and to our customers like @Replit, @clay, @TrustVanta, @Cloudflare, @Rippling, @Cisco, @Workday, and many more for their trust. Read more here about what this means for the future of building agents: blog.langchain.com/series-b/?utm_…

Saw @arafatkatze's brilliant thread on the 3-state agent pattern and took it as a challenge! 🚀 Built it with LangChain v1 alpha's new middleware concept - turns out this elegant pattern maps perfectly to middleware's lifecycle hooks. The simplicity is beautiful. 🧵👇

@teknium Now `cursor [folder]` takes multiple seconds instead...

No, no I do not!

@levelsio @tomosman @vonderleyen 🇨🇿🫡

@tomosman @vonderleyen Why Portugal why

🇪🇺 My fellow Europeans You have to fight ChatControl 💪 Don't let @vonderleyen read your chats! metalhearf.fr/posts/chatcont…

@alexyang Long overdue really

I think we need AsyncContext (AsyncLocalStorage) in TC39 Stage 3, ASAP

🚀 Excited to share my first big contribution since joining @LangChain a month ago! We’re introducing Middleware in LangChain 1.0 — a new agent abstraction that finally gives developers full control over context engineering. Flexible. Composable. Adaptable — supports implementing different agent anthropologies like reflection, swarms, supervisors, and more It's in alpha but go try it out, I would love your feedback 😊 Blog 👉 blog.langchain.com/agent-middlewa… I am gonna post a lot of agent content within the next time, so stay tuned 🤟 More to come soon ✨

🚀Agent Middleware The core agent loop is dead simple - but there are lots of small variants to state management or steps that you may want to tweak Middleware lets you do that! New in LangChain 1.0alpha Blog: blog.langchain.com/agent-middlewa… Docs: docs.langchain.com/oss/python/lan…