Anthropic's Claude Code, OpenAI's Deep Researcher, and Manus's general purpose agent have demonstrated that agents can be amazingly effective on complex, long-running tasks. We call these Deep Agents because they have a few key differentiators from earlier forms of agents. In our new LangChain Academy course, Deep Agents with LangGraph, you'll learn their key characteristics and how to implement them in your own Deep Agent.So what makes these agents different. Under the hood, they use a simple ReAct tool-ca ...

Core Viewpoint - LangChain has launched Open SWE, an open-source asynchronous coding agent designed to run in the cloud and handle complex software development tasks, marking a shift from real-time "co-pilot" assistants to more autonomous agents integrated into developers' workflows [2][3]. Group 1: Functionality and Features - Open SWE connects directly to GitHub repositories, allowing developers to assign tasks via GitHub Issues or a dedicated UI, enabling the agent to research codebases, generate detailed plans, write and test code, review, and open pull requests upon completion [2]. - The tool is designed to manage long contexts and long-term tasks, operating in a secure, isolated Daytona sandbox that allows the agent to execute shell commands without compromising the host environment [2]. - Open SWE emphasizes human control, allowing developers to interrupt the agent mid-task, request changes, or provide new instructions without needing to restart the process [3]. Group 2: Architecture and Quality Assurance - The multi-agent architecture of Open SWE, consisting of Manager, Planner, Programmer, and Reviewer, is crucial for generating high-quality code, with the Reviewer checking outputs for errors before any pull requests are created [3]. - The platform is built on LangGraph, optimized for long-running agents, providing persistence, scalability, and deployment flexibility [5]. Group 3: Community and Feedback - Open SWE is now available on GitHub, offering complete documentation for developers looking to extend, customize prompts, or integrate it into internal systems, positioning the project as both a production-ready assistant and a foundation for community innovation [7]. - Early reactions have been mixed, with some users expressing skepticism about the capabilities of LangChain and its ecosystem, indicating potential concerns about the reliability of the technology [6].

Core Viewpoint - The article discusses various mainstream AI Agent frameworks, highlighting their unique features and suitable application scenarios, emphasizing the growing importance of AI in automating complex tasks and enhancing collaboration among agents [1]. Group 1: Mainstream AI Agent Frameworks - Current mainstream AI Agent frameworks are diverse, each focusing on different aspects and applicable to various scenarios [1]. - The frameworks discussed include LangGraph, AutoGen, CrewAI, Smolagents, and RagFlow, each with distinct characteristics and use cases [1][2]. Group 2: CrewAI - CrewAI is an open-source multi-agent coordination framework that allows autonomous AI agents to collaborate as a cohesive team to complete tasks [3]. - Key features of CrewAI include: - Independent architecture, fully self-developed without reliance on existing frameworks [4]. - High-performance design focusing on speed and resource efficiency [4]. - Deep customizability, supporting both macro workflows and micro behaviors [4]. - Applicability across various scenarios, from simple tasks to complex enterprise automation needs [4][7]. Group 3: LangGraph - LangGraph, created by LangChain, is an open-source AI agent framework designed for building, deploying, and managing complex generative AI agent workflows [26]. - It utilizes a graph-based architecture to model and manage the complex relationships between components in AI workflows [28]. Group 4: AutoGen - AutoGen is an open-source framework from Microsoft for building agents that collaborate through dialogue to complete tasks [44]. - It simplifies AI development and research, supporting various large language models (LLMs) and advanced multi-agent design patterns [46]. - Core features include: - Support for agent-to-agent dialogue and human-machine collaboration [49]. - A unified interface for standardizing interactions [49][50]. Group 5: Smolagents - Smolagents is an open-source Python library from Hugging Face aimed at simplifying the development and execution of agents with minimal code [67]. - It supports various functionalities, including code execution and tool invocation, while being model-agnostic and easily extensible [70]. Group 6: RagFlow - RagFlow is an end-to-end RAG solution focused on deep document understanding, addressing challenges in data processing and answer generation [75]. - It supports various document formats and intelligently identifies document structures to ensure high-quality data input [77][78]. Group 7: Summary of Frameworks - Each AI Agent framework has unique characteristics and suitable application scenarios: - CrewAI is ideal for multi-agent collaboration and complex task automation [80]. - LangGraph is suited for state-driven multi-step task orchestration [81]. - AutoGen is designed for dynamic dialogue processes and research tasks [86]. - Smolagents is best for lightweight development and rapid prototyping [86]. - RagFlow excels in document parsing and multi-modal data processing [86].

Our latest LangChain Academy course Deep Research with LangGraph is now live. In this course, you'll learn to build your own deep research agent from scratch, using LangGraph. You'll find that it's a manageable project that you can get up and running quickly.Along the way, you'll use a multi-agent architecture and explore prompting techniques, like adding thinking steps that improve performance and offer insights into the model's decision making. Deep research has broken out as one of the most popular agent ...

Educational Offerings - LangChain Education provides various learning methods, including courses, YouTube videos, and documentation [1] - LangChain Academy offers three types of courses: Foundational, Project, and Quickstart [1] Course Types - Foundational courses offer methodical learning from introduction to mastery and require more time to complete [2] - Project courses guide users through building specific projects, such as a Deep Research agent, and can typically be completed in a few hours [2] - Quickstart courses provide a quick introduction or review of a topic [2] Additional Resources - LangChain publishes educational videos on YouTube covering current topics, product features, and in-depth series [3] - LangChain provides extensive documentation with examples and step-by-step instructions [3]

Core Viewpoint - The article emphasizes the importance of "Context Engineering" as a systematic approach to optimize the input provided to Large Language Models (LLMs) for better output generation [3][11]. Summary by Sections Introduction to Context Engineering - The article highlights the recent popularity of "Context Engineering," with notable endorsements from figures like Andrej Karpathy and its trending status on platforms like Hacker News and Zhihu [1][2]. Understanding LLMs - LLMs should not be anthropomorphized; they are intelligent text generators without beliefs or intentions [4]. - LLMs function as general, uncertain functions that generate new text based on provided context [5][6][7]. - They are stateless, requiring all relevant background information with each input to maintain context [8]. Focus of Context Engineering - The focus is on optimizing input rather than altering the model itself, aiming to construct the most effective input text to guide the model's output [9]. Context Engineering vs. Prompt Engineering - Context Engineering is a more systematic approach compared to the previously popular "Prompt Engineering," which relied on finding a perfect command [10][11]. - The goal is to create an automated system that prepares comprehensive input for the model, rather than issuing isolated commands [13][17]. Core Elements of Context Engineering - Context Engineering involves building a "super input" toolbox, utilizing various techniques like Retrieval-Augmented Generation (RAG) and intelligent agents [15][19]. - The primary objective is to deliver the most effective information in the appropriate format at the right time to the model [16]. Practical Methodology - The process of using LLMs is likened to scientific experimentation, requiring systematic testing rather than guesswork [23]. - The methodology consists of two main steps: planning from the end goal backward and constructing from the beginning forward [24][25]. - The final output should be clearly defined, and the necessary input information must be identified to create a "raw material package" for the system [26]. Implementation Steps - The article outlines a rigorous process for building and testing the system, ensuring each component functions correctly before final assembly [30]. - Specific testing phases include verifying data interfaces, search functionality, and the assembly of final inputs [30]. Additional Resources - For more detailed practices, the article references Langchain's latest blog and video, which cover the mainstream methods of Context Engineering [29].

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improv ...

[Music] My name is John Gutsinger. Uh I work for Cisco. I'm a principal engineer and I work in the technical assistance center or TAC for short.Uh really I'm focused on AI engineering, agentic engineering in the face of customer support. We've been doing a IML for you know a couple years now maybe five or six years. really it started with trying to figure out how do we handle these mass scale issues type problems right where uh some trending issues going to pop up we know we're going to have tens of thousan ...

Company Overview - Vizian serves 97% of academic medical centers in the US, over 69% of acute care hospitals, and more than 35% of the ambulatory market [1] - Vizian is developing a generative AI platform to improve healthcare providers' data access and analysis [2] Challenges Before Langraph and Langsmith - Scaling LLM queries using Azure OpenAI faced token limit issues, impacting performance [3] - Limited visibility into system performance made it difficult to track token usage, prompt efficiency, and reliability [3] - Continuous testing was not feasible, leading to reactive problem-solving [4] - Multi-agent architecture introduced complexity, requiring better orchestration [4] - Lack of observability tools early on resulted in technical debt [4] Impact of Integrating Langraph and Langsmith - Gained the ability to accurately estimate token usage, enabling proper capacity provisioning in Azure OpenAI [5] - Real-time insights into system performance facilitated faster issue diagnosis and resolution [6] - Langraph provided structure and orchestration for multi-agent workflows [6] - Resolved LLM rate limiting issues by optimizing token usage and throughput allocation [7] - Development and debugging processes became significantly faster [8] - Shift to automated continuous testing dramatically improved system quality and reliability [8] - Rapidly turn beta user feedback into actionable improvements [8] Recommendations - Start with a slim proof of concept and model one high impact user flow in Langraph [9] - Integrate with Langsmith from day one and treat every run as a data point [9] - Define a handful of golden query response pairs upfront and use them for acceptance testing [9] - Budget a short weekly review of Langsmith's run history [9]

Industry Focus: Autonomous Agents in Healthcare - The workshop explores building autonomous agents for managing complex processes like multi-day medical treatments [1] - The system aims to help patients self-administer medication regimens at home [1] - A key challenge is enabling agents to adhere to protocols while handling unexpected patient situations [1] Technology Stack - The solution utilizes a hybrid system of code and prompts, leveraging LLM decision-making to drive a web application, message queue, and database [1] - The stack includes LangGraph/LangSmith, Claude, MCP, Nodejs, React, MongoDB, and Twilio [1] - Treatment blueprints, designed in Google Docs, guide LLM-powered agents [1] Agent Evaluation and Human Support - The system incorporates an agent evaluation system using LLM-as-a-judge to assess interaction complexity [1] - The evaluation system escalates complex interactions to human support when needed [1] Key Learning Objectives - Participants will learn how to build a hybrid system of code and prompts that leverages LLM decisioning [1] - Participants will learn how to design and maintain flexible agentic workflow blueprints [1] - Participants will learn how to create an agent evaluation system [1]