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?

🥯Join us for an intimate breakfast with the LangChain community. Whether you're a founder, researcher, or engineer, let’s connect over bagels and coffee to talk about the future of agents. The Details:📍 Where: LangChain HQ, SF (SOMA) 🗓️ When: Jan 30, 2026 | 8:00–9:30 AM PST 🤝

🚨FLIGHTSCOPE BLACK FRIDAY SALE $1,200 OFF Mevo Plus Golf Simulators!

📊🤖 LangAlpha: AI Equity Analysis Platform Made by the LangChain Community LangAlpha automates equity research from queries. Using LangGraph's multi-agent system, agents synthesize market data, news, and financials into institutional-grade reports in minutes. Check out the

🏗️🤖 Building AI Applications from Scratch Made by the LangChain Community Learn complete AI app architecture through a 5-step pipeline using LangChain's Document Loaders, Vector Stores, Retrievers & Agents—solving context limits and hallucinations. 📺 Watch:

🗄️ Oracle AI Developer Hub Production-ready AI agents with persistent storage. Six memory patterns for LangChain agents using Oracle AI Database for scalable context management, plus RAG with evaluation frameworks. 🔗 Repository: https://t.co/vs37oe4cum Made by the LangChain

Step out in high style at your next formal event and turn some heads with Gentleman's Guru. Shop the latest styles in men's formal wear and accessories for the modern gentleman. Get FREE shipping and EASY returns Get assistance from our Experts Award Winning Brand

🚀 Serverless Deep Agent with LangGraph Thomas builds a stateful AI agent on AWS Bedrock AgentCore, solving state management with LangGraph's checkpointing and langgraph-checkpoint-aws integration. 📺 Watch the full tutorial: https://t.co/ZJeSp3NdMP Made by the LangChain

🧠 Persistent Memory with zkStash SDK Made by the LangChain Community zkStash is a TypeScript SDK for persistent memory in AI agents. Integrates with LangChain via MCP tools or middleware, using Zod schemas for structured storage of preferences and conversations. 📚 Docs:

🚀 Building Enterprise Agents with Deep Agents Learn to build and deploy enterprise AI agents using Deep Agents and Runloop. Uses Runloop to run code safely in sandboxes 📺 Watch the full tutorial: https://t.co/WOPY873OUA Made by the LangChain Community

Claude Code 🤝 LangSmith Curious what Claude Code is doing behind the scenes? Or want observability into critical workflows that you’ve set up with Claude Code. With our new Claude Code → LangSmith integration, you can view every 🤖 LLM call and 🔧 tool call Claude Code makes.

Earning shouldn't disappear behind a paywall. Earn 2% APY on $USDG with Kraken. No subscription required. Power users can earn more with Kraken+

Managing Deepagents Memory Memory allows agents to learn tasks, knowledge, or preferences over time. Here, we overview two ways to update Deepagent-CLI memory: direct instruction and reflection over past Deepagent sessions. 📹: https://t.co/Dr2O2OArSZ

Ready to build your first AI agent? 🤖✨ Join @LangChainAI x @TavilyAI on Feb 5th at Herald Square for an evening dedicated to women and gender-diverse builders. In this hands-on workshop, you will build and deploy your own AI agent, no coding required. What’s in store:🛠️

🔗 New LangChain Academy Course: Introduction to LangChain (Python) 🔗 Learn how to build with LangChain – our open source framework that makes it easy to start building agents with any model provider. In this course, you’ll create agents that can reason, use tools, and take

Build an MCP agent with Claude — and dynamically discover tools across @Cloudflare's MCP servers 🧠⚡ No hard-coded APIs. No giant tool lists. Claude uses @AnthropicAI's native MCP toolset + tool search to discover and invoke Cloudflare tools on demand — including browser

Finding your Pydantic models no longer work with @LangChainAI 1.0's create_agent? Clara Chong ran into this and shares a helper to convert them to TypedDicts while preserving metadata. https://t.co/rcIHaRC9Gp

⚖️ Pairwise Annotations: Scores are hard, preferences are easy. Agents handle tasks that are tough to score but easy to compare: support responses where tone matters, code refactors where both work but one feels cleaner, product specs where "good" is subjective. In practice,

That’s not a joke That’s 12,5% up in first hour That’s record sales That’s a huge momentum $NVDA $PLTR $meta $Amzn $SPY

LangSmith + Claude Code / Deepagents Pairing LangSmith tracing w/ code agents provides a powerful feedback loop. Here, we show examples of that w/ langsmith-fetch + Claude Code / Deepagents. langsmith-fetch CLI: https://t.co/v7Cs9o70NL 📹: https://t.co/t4QHB7XPBK

We’re excited to share that LangSmith, the agent engineering platform for observability, evaluation, and deployment, has been named one of @brexHQ's Top 25 Fastest-Growing Software Vendors of 2025 🎉

Fastweb + Vodafone (Swisscom Group), one of Europe’s leading telecom providers, is building Super TOBi, which brings agentic customer service to massive scale. Using LangSmith, they are: 🔹Achieving 90% response correctness and 82% resolution rates across ~9.5M customers

Read the full report here ➡️ https://t.co/Ia2LnXNcEE

AMAC: sign up for a 90-day trial today to find out why Scott Jennings and millions of Americans are taking a stand for their values and joining AMAC.

Coding agents were the most common type of agents that respondents used in their daily workflows, led by tools like Claude Code, Cursor, and GitHub Copilot.

Meanwhile, orgs are earlier in their evals usage, with around half of respondents running offline evals on test sets and just over one-third running online evals on production data.