The agent engineering platform and open-source AI frameworks
AI & Data Infrastructure
Material only: impact 4+ or flagged, unmuted, with a real source behind it. Newest first.
LangChain is co-hosting an in-person event with AWS and NVIDIA focused on building and scaling agentic AI workloads using Amazon EKS, NVIDIA technologies, and LangChain. The partnership with two major hyperscalers for a joint event signals growing enterprise ecosystem alignment and go-to-market credibility for LangChain.
LangChain has published content (shared via its Japanese community account) covering lessons from scaling AI agents in healthcare and life sciences, featuring named customers Madrigal Pharmaceuticals, Abridge, and Vizient. This demonstrates real enterprise traction in regulated verticals and strengthens LangChain's positioning as the go-to agent engineering platform for healthcare.
LangChain published a first-party blog post announcing that Jev-as-a-Judge is now available in LangSmith, its evaluation and observability platform. This extends LangSmith's eval capabilities with a dedicated judge model, strengthening LangChain's position as the end-to-end agent engineering platform and deepening the LangSmith product moat.
LangChain's own blog published 'Can Jev Be a Better Agent Evaluator?', examining TypeSafe AI's Jev model as an alternative to LLM-as-judge approaches for agent evaluation on LangSmith. This first-party content signals LangChain's strategic focus on making LangSmith the go-to evaluation platform for production AI agents.
LangChain has open-sourced DeepAgents, a ready-made agent harness featuring sub-agents, task planning, a virtual filesystem, and durable LangGraph runs. This is a first-party product release that extends LangChain's open-source ecosystem and reinforces its position as the go-to agent engineering platform. The release strengthens the LangGraph/LangSmith flywheel by giving developers a production-ready scaffold to build on.
LangChain's blog details how Included Health used LangGraph and Deep Agents to build federated AI agents for healthcare navigation. The case study demonstrates LangGraph's suitability for complex, multi-agent healthcare workflows, adding a high-profile enterprise reference in a regulated vertical.
LangChain published production case studies from three healthcare organisations — Madrigal Pharmaceuticals, Abridge and Vizient — all of which independently adopted multi-agent architectures to solve the same scaling bottleneck. This demonstrates growing enterprise traction for LangChain in regulated, high-stakes verticals and strengthens its position as the go-to agent engineering platform for healthcare AI teams.
LangChain's blog features how Schneider Electric, Vodafone and monday.com are scaling AI agents across Europe and the Middle East, providing first-party evidence of major enterprise adoption. This is a meaningful customer validation signal, demonstrating LangChain's traction with large multinationals in two high-growth regions. It reinforces LangChain's position as the go-to agent engineering platform for enterprise deployments.
Kept for the record; these do not count toward heat. Unverified means the only source is a post from an account we do not know.
Source items behind the signals, last 30 days
31 roles posted in 30 days · 76 in 90 · 8 senior · 23 locations
Their own blog, changelog and newsroom, newest first
The Reliability Layer for Healthcare AI: Common LangSmith Use Cases
Jev-as-a-Judge Is Now Available in LangSmith
Can Jev Be a Better Agent Evaluator?
Building a Harness with Jev
Building an Agent Harness for Life Sciences: Introducing Deep Life Sci
How Included Health Built Federated Healthcare Agents with LangGraph and Deep Agents
Scaling Agents in Healthcare & Life Sciences: Lessons from Madrigal Pharmaceuticals, Abridge, and Vizient
Scaling Agents in Europe & The Middle East: Lessons from Schneider Electric, Vodafone, and monday.com
How We Built LangChain’s Paid Media Agent
Connections: managed credentials and per-caller identity for Managed Deep Agents
How Credit Genie keeps codebase docs fresh with OpenWiki
How we built LangChain’s GTM Agent
Organizing Context in a Multi-Agent Harness
MCP in LangChain: Stateless Protocol, Elicitation, and More!
August 2026: LangChain Newsletter — Managed Deep Agents, LLM Gateway, and More
Reflections on Three Years of Building LangChain
Pushing LangSmith to new limits with Replit Agent's complex workflows
How Podium optimized agent behavior and reduced engineering intervention by 90% with LangSmith
How Factory used LangSmith to automate their feedback loop and improve iteration speed by 2x
Why We Rebuilt LangChain’s Chatbot and What We Learned
Introducing Interrupt: The AI Agent Conference by LangChain
LangSmith: Redesigned product homepage and Resource Tags for better organization
LangChain State of AI 2024 Report
January 2026: LangChain Newsletter
Aligning LLM-as-a-Judge with Human Preferences
LangSmith LLM Gateway: Runtime Controls for Agents
How LangSmith and LangChain OSS Help You Meet EU AI Act Requirements
Announcing LangGraph v0.1 & LangGraph Cloud: Running agents at scale, reliably
LangChain's Second Birthday
LangGraph Platform is now Generally Available: Deploy & manage long-running, stateful Agents
X and Hacker News posts that resolved to a signal
Using Azure Blob Storage as a durable filesystem for LangChain Deep Agents https://t.co/sfhwAHHb1F #azure
Using Azure Blob Storage as a durable filesystem for LangChain Deep Agents https://t.co/sfhwAHHb1F #azure
Agentic systems are moving from demos to real workflows. 🤖 Join @Auth0, @LangChain, at the Zürich AI Meetup on September 29 for an evening of Agentic Chains, practical AI workflows, and conversations with the people building them. RSVP: https://t.co/gYuPG2NTf6 https://t.co/P6RRS9gKeU
langchain-core 1.6.4 deprecates built-in chat history, pushing memory to external stores. When your agent's conversation state lives in Redis or Postgres, those connection strings are secrets. @LangChain builders: that's exactly what Vault is for.
TypeSafe is pushing hard on this idea of “composable AI” but LangChain has embodied composable AI since day one. With new models like Jev, we’re decomposing the agent loop and moving more intelligence into the glue that holds it all together. Watch this space. https://t.co/a3FLrplb34
Instructor vs LangChain for structured LLM outputs: LangChain’s LCEL adds a layer of obfuscation that makes debugging schema failures a nightmare. Instructor leverages Pydantic directly to patch the provider SDK, ensuring your data model is the source of truth.
LangChain Community Spotlight: AI transforms property management AppFolio's Realm-X Assistant saves 10+ hours weekly by automating tenant inquiries, maintenance requests, billing through LangChain/LangGraph/LangSmith. Read the full case study → https://t.co/HdQt5aUmx2
𝗪𝗵𝘆 𝗮𝗴𝗲𝗻𝘁 𝗯𝘂𝗶𝗹𝗱𝗲𝗿𝘀 𝗰𝗮𝗿𝗲: most agent steps are tiny decisions. "Is this tool call safe?" "Does this need the frontier model?" "Is it done?" Decide fast, generate only when needed. Vercel and LangChain shipped integrations within hours of launch. https://t.co/6869SpbF7R
What tool went “legacy” on you this week? LangChain, a model, an “agent” product — drop it below.
I was mid-LangChain. Then Jev by TypeSafe dropped: 100–500× faster structured decisions. Then Grok 4.7. Then GPT-6. Can the labs pause 5 minutes so one thing actually lands.
Yesterday: learn LangChain. Today: AI harnesses. Tomorrow: why are you still using an LLM? The stack is moving faster than anyone can finish a tutorial.
Be honest: You're shipping an AI agent to production this quarter. Are you reaching for LangChain or building a Custom Agent Loop from scratch? 👇 https://t.co/lbCNGB7lTd
this agent 1. browses the web with stagehand from @browserbase 2. prepares payment with the link CLI from @stripe 3. asks for approval before the charge 4. places the order, ready for pickup! official @LangChain / link integration coming soon! https://t.co/MADlDW6sIk
My curiousity to ignoring noise and trying to find the fundamentals of whatever tech trend helped me find out Langchain and their Technology. Now Graph Engineering is a trend even though it's just a structure of writing Agentic code in @LangChain. https://t.co/2awl3sgdPr
Built a model router with Jev + LangChain 🚀 Request → Jev classifier → difficulty → right LLM Fast models for simple tasks. Powerful models only when needed. Also includes routing evaluation, cost/latency comparison, and confusion-matrix analysis. 🔗 https://t.co/4i1rxEcijG
Join @AWScloud, @NVIDIA, and LangChain for an in-person session focused on how teams can build flexible infrastructure for developing and scaling agentic AI workloads. We’ll explore how Amazon EKS, NVIDIA technologies, and LangChain can come together to give teams more https://t.co/B4nARybVZO
A PR from a Slack thread ⚙️ LangChain Managed Deep Agents: tag Patch, describe the feature, get a GitHub PR with the diff ready to review. https://t.co/gDou5e5dJJ
Are Langchain and AI Agent frameworks dead? Why will someone use these rather than AI Agentic frameworks from the leading LLMs (Claude & OpenAI)?
Hierarchical supervisor tree: best for routing across specialists, and centralized verification contains errors (4.4x vs 17.2x amplification). Pays a supervisor turn per hop. LangChain now steers teams toward supervisors used 'directly via tools.'
Unreal Agent reports up to 40% cost savings vs Codex. Async tool management reduces model overhead by eliminating waits and polls. Is this async pattern viable for all complex RAG workflows? #RAG #Agent #Codex #LangChain
i was informed of this new product update on a live LangChain <> Jev webinar with 500 people. the speed at which the team operates is unreal. 📈 https://t.co/9xDD1xtjNj
LangChain put Jev inside their own agent loop and showed the three jobs they hand it In the demo an LLM took about 5 seconds to say whether a text contains PII, and Jev answered immediately with 98% So their coding agents can ask Jev how hard a task is and save the powerful https://t.co/JRFE9ZTDwK https://t.co/noPP2TqUws
🗣️ Overheard at The Persistent Context Sprint Hackathon at MongoDB.local Build Fest, in partnership with @cerebral_valley, @cursor_ai, @OpenRouter, @ElevenLabs, @FireworksAI_HQ, and @LangChain: "...anyone with a real problem and a willingness to start can build something that https://t.co/xeH4ajUGvT
NYC agent builders: tomorrow night is the Agentic Lounge at Fraunces Tavern, ahead of LangChain Interrupt. Talk production agents with Focused’s principal engineers over cocktails, bites, and live piano. No Interrupt ticket needed: https://t.co/9ZDkOe89o3
Per-turn skill routing for LangChain deepagents, with @typesafeai's Jev as the judge. Measured on 236 skills and 55 conversations: 3.8× less context per turn, the right skill reached the model in 86% of turns, against 58% with the full catalog. MIT: https://t.co/3HwSMCCkdm
LangChain co-founder Harrison Chase: "There's a harness that orchestrates a model and some context." In under 24 minutes, he explains the loop behind tool use and context. That helps you understand what changes when you switch runtimes. I'd put this free talk ahead of many https://t.co/Wttml5dy6X https://t.co/ERG2bc1DLi
I had a very similar reaction. Here's my blogpost https://t.co/x8vP2POJMT where I put this subsumption model to work in an actual neurosymbolic System 1/2 architecture, as a @LangChain (LangGraph) harness. https://t.co/msptq6JvQe
☁️ AzureBlobBackend gives LangChain agents durable, shareable files in Blob Storage. The hard part isn’t persistence—it’s deciding which agent-generated junk deserves to survive. https://t.co/YxM1qyozuu #CloudStorage #Langchain #AzureBlobStorage #DeepAgents https://t.co/RFIYaHrDic
Using Azure Blob Storage as a durable filesystem for LangChain Deep Agents https://t.co/uIIM7ScLGd #microsoft
Cloudflare Python Workers: now GA. Python is first-class on the edge. No JavaScript glue code needed. → FastAPI / Django / Flask native → openai, langchain, mcp work OOB → Postgres via Hyperdrive support