Explore the unique challenges of observing and evaluating Deep Agents in production. Deep Agents represent a shift in how AI systems operate – unlike simple chatbots or basic RAG applications, these agents run for extended periods, execute multiple sub-tasks, and make complex decisions autonomously. In this session, we'll dive into practical approaches for gaining visibility into Deep Agent behavior and measuring their effectiveness using LangSmith. Learn more about Deep Agents here: https://blog.langchain. ...

Hey, this is Lance. I want to talk a bit about the deep agents package that we recently released. Now, the length of tasks that an agent can take every seven months.And we see numerous examples of popular longrunning agents like Claude Code, Deep Research, Manis. The average Manis task, for example, can be up to 50 different tool calls. And so, it's increasingly clear that agents are needed to do what we might consider deeper work or more challenging tasks that take longer periods of time.Hence, this term d ...

Deep Agents Overview - Deep Agents is an open-source agent harness incorporating planning, computer access, and sub-agent delegation tools, commonly found in agents like Manis and Cloud Code [1][46] - The harness is designed to be easily adaptable with custom prompts, tools, and sub-agents [2][47] Key Features and Tools - Deep Agents provides built-in tools such as planning, sub-agent delegation, and file system operations [6][7] - The built-in tools enable interaction with the file system, shell command execution, planning via to-dos, and task delegation [8] - Custom tools, instructions, and sub-agents can be added to Deep Agents to tailor it for specific use cases [6][47] Quick Start and Research Application - The Deep Agent quick start repo offers examples for different use cases, starting with research [2][5] - The research quick start includes tools like a search tool (using Tavi search API) and an optional "think" tool for auditing agent trajectory [12][13][14] - Task-specific instructions and sub-agents can be supplied to Deep Agents for any given use case [12] Agent Loop and Middleware - Deep Agents utilizes Langraph for orchestrating the agent loop, which involves the language model (LLM) calling tools in a loop [29] - Middleware serves as hooks within the agent loop, allowing for actions like summarization when context exceeds 170,000 tokens [30][32] - Middleware can provide tools to the agent, such as file system middleware, and perform actions like summarization and prompt caching [31][34] File System and State Management - By default, Deep Agents writes to an internal in-memory state object, but it supports different backends like a sandbox or local file system [37][38] - File reading and writing operations occur within the Langraph state object, enabling easy retrieval into the LLM's context window [40] Deployment and Visualization - Deep Agents can be run in a Jupyter notebook for interactive inspection or deployed as an application using Langraph [10][44] - A UI can be connected to the local Langraph server for visualizing generated files and agent interactions [3][45]

Check this out. I just asked an agent to answer one of the world's greatest debates. Is Messi or Ronaldo the greatest soccer player of all time.This isn't an easy question to answer, and it definitely requires a good amount of research. The agent automatically spawned two parallel sub agents to look into each of their achievements. This meant searching the web over a dozen times, compiling a comprehensive report with cited sources.To be extra thorough, the agent then critiqued its own report and plugged any ...

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 ...

Deep Agent Architecture - Deep agents utilize a planning tool to strategize task execution [4][5] - They employ a file system for organized context and information management, preventing context window overload [5] - Deep agents leverage specialized sub-agents to execute specific tasks, such as research or critique [5][6][18] - A detailed system prompt guides the overall operation of agents and sub-agents [6][10] Implementation and Usage - The process involves cloning the deep agents JS repository and the deep agents UI repository [7][13][14][19] - Configuration requires setting up environment variables, including API keys for web search (Tilli API key) and LLM provider (Anthropic API key), as well as specifying the Langraph server URL and agent ID [8][15][16][19] - The deep agent is instantiated using the `create deep agent` function, which requires a list of tools, instructions, and optionally, sub-agents [9][10] - The Langraph server is initiated using the command `npx langchain langraph cli dev` [8][13] - The deep agents UI runs on localhost 3000, allowing users to interact with the agent [16]

Deep agents are a form of agents that plan, reason, and act over longer time horizons. We built a dedicated UI for viewing and interacting with these agents that show its plan, the status of the file system that it uses, and any sub aents it kicks off. My name is Nick.I'm an engineer at Langchain, and today you'll learn how to set up this UI. Now, as a quick refresher, we can think of deep agents as a variant of the generic React tool calling architecture. Under the hood, deep agents still follow the same i ...

Deep Agent Characteristics - Deep agents utilize a planning tool to manage long-term tasks, enabling cohesive action over extended periods [3][5][9] - Sub-agents are employed to focus on specific areas, preserving context and allowing for specialized expertise, which can improve overall results [3][10][11][12][13][15] - A file system is used to offload context, preventing performance degradation of the LLM by storing and accessing information as needed [3][16][17][18] - Detailed system prompts, often hundreds or thousands of lines long, are crucial for guiding the agent's behavior and tool usage [3][21][22][23] Deep Agent Implementation - Deep agents operate using the same tool-calling loop as simpler agents, but are distinguished by their prompts and tools [3][4][5] - Planning tools can be simple, such as a "to-do write" tool that generates and modifies task lists within the model's context [7][8] - Sub-agents can have specialized expertise and different permissions, allowing for focused work and better results [13][14] - File systems allow agents to manage context by referencing files instead of directly including large observations in the LLM context [17][18] Deep Agent Benefits - Deep agents are capable of handling longer time horizon and more complex tasks compared to naive LLM implementations [4][5] - Sub-agents facilitate context preservation, preventing the main agent's context from being polluted by sub-tasks and vice versa [11][12] - Reusable sub-agents can be created and used across different agents, promoting efficiency and modularity [14]