LangChain、LangGraph与LangSmith各做什么

When I started learning agentic AI, I kept running into three names: LangChain, LangGraph, LangSmith. They sound almost the same. What does each one actually do? Do you need all three? Let me clear the confusion for you in 30 seconds. >> 𝗜𝘁 𝘀𝘁𝗮𝗿𝘁𝘀 𝘄𝗶𝘁𝗵 𝗮𝗻 𝗟𝗟𝗠. It can answer questions, write code, and summarize documents. But it can't reach your database, call your APIs, or remember last week's conversation on its own. So developers wrapped code around it: prompts, document retrieval, API calls, output parsers. Everyone ended up writing the same glue code, and switching models meant touching the whole app. >> 𝗟𝗮𝗻𝗴𝗖𝗵𝗮𝗶𝗻 𝗳𝗶𝘅𝗲𝘀 𝘁𝗵𝗶𝘀. It gives you ready-made building blocks to connect models, tools, retrievers, and prompts into one working app. Then we see the problem - A simple chain works when every step follows the last one. - Real agents don't behave like that. If a tool fails, the agent must retry. It has to pick between two paths. It needs a human to approve an action. Or the app crashes halfway through a long task. Handling all that with loops, flags, and custom retry code gets ugly fast. >> 𝗟𝗮𝗻𝗴𝗚𝗿𝗮𝗽𝗵 𝗳𝗶𝘅𝗲𝘀 𝘁𝗵𝗶𝘀. You build workflows where steps can loop, branch, share state, and resume after a failure. Think of it as a stateful workflow engine for AI agents. Now you ship it. Real users are on it. Then someone says, "The agent gave me a wrong answer." Your logs look healthy. But what actually went wrong? - Was the retrieved context bad? - Did a tool return wrong data? - Did the model ignore your instructions? - Did your last prompt change break something? - And what did that one request cost? Normal app logs won't tell you. >> 𝗟𝗮𝗻𝗴𝗦𝗺𝗶𝘁𝗵 𝗳𝗶𝘅𝗲𝘀 𝘁𝗵𝗶𝘀. It traces each run, shows prompts and tool calls, tracks latency and token usage, and lets you test outputs against datasets before you roll out changes. Think of it as observability plus evaluation for LLM apps. 𝗧𝗼 𝘀𝘂𝗺𝗺𝗮𝗿𝗶𝘀𝗲 LangChain → connects LLMs to tools, APIs, and data LangGraph → manages state, loops, retries, human approvals LangSmith → traces, debugs, and evaluates quality You don't need all three on day one. - Start simple. Add LangGraph when your workflow needs state and branching. - Add LangSmith when you need to see what's happening in production. Don't try to learn every framework. Learn the problem each tool solves.