介绍环境代理
Most AI apps today follow a familiar chat pattern ("chat" UX). Though easy to implement, they create unnecessary interaction overhead, limit the ability of us humans to scale ourselves, and fail to use the full potential of LLMs.Over the past six months, we've been exploring a different approach at LangChain: agents that respond to ambient signals and demand user input only when they detect important opportunities or require feedback. Rather than forcing users into new chat windows, these agents help save your attention for when it matters most.
如今大多数AI应用程序都遵循一种熟悉的聊天模式（“聊天”用户体验）。虽然易于实现，但它们会产生不必要的交互开销，限制我们人类自我扩展的能力，并未能充分利用LLM的潜力。在过去的六个月里，我们在LangChain探索了一种不同的方法：响应环境信号的代理，仅在检测到重要机会或需要反馈时才要求用户输入。这些代理不强迫用户进入新的聊天窗口，而是帮助你在最重要的时候节省注意力。
We built LangGraph to make these patterns easy to implement. Today we're sharing our first reference implementation: an email assistant that demonstrates key ambient agent patterns. Over the next few days, we'll release additional examples and tooling to help you build your own ambient workflows.
我们构建了 LangGraph 以使这些模式易于实现。今天我们分享了我们的第一个参考实现：一个展示关键环境代理模式的电子邮件助手。在接下来的几天里，我们将发布更多示例和工具，帮助你构建自己的环境工作流程。
What is an ambient agent?
什么是环境代理？
When using ChatGPT (or any other chatbot), they rely on you to initiate the conversation. The agent is kicked off by the human sending a message.
使用 ChatGPT（或任何其他聊天机器人）时，它们依赖你来启动对话。代理由人类发送消息启动。
This is great for some use cases, but also severely limiting for others. It requires the user to go into the chat interface and send a message every time they want the agent to do work. There is a lot of overhead in having the agent start work.
这对于某些用例来说非常好，但对于其他用例来说也有很大的限制。它要求用户每次想让代理工作时都进入聊天界面并发送消息。让代理开始工作有很多开销。
An additional limitation is you can only have one conversation at a time. This makes it hard for us humans to scale ourselves - an agent can only be doing one thing for us at a time.
另一个限制是你一次只能进行一个对话。这使得我们人类很难扩展自己——一个代理一次只能为我们做一件事。
If we think about a UX paradigm that allows us to overcome these limitations, it should exhibit two key characteri...