推文原文

• learn: python, git, the terminal, http and json, basic sql, fastapi

• practice: build a cli tool that calls a public api and writes clean json to disk

• why: ai engineering is software engineering first, and every stage below assumes you can ship a working endpoint

• learn: prompting, structured outputs with pydantic, tool calling, streaming, conversation state, token cost

• practice: build an invoice parser that returns a typed python object, then give a model 3 tools and let it pick

• why: this is the actual job, and most people skip straight past it to agents

• learn: embeddings, chunking, vector stores, metadata filtering, reranking

• practice: ingest 20 pdfs and ship an endpoint that returns a cited answer from the top 5 chunks

• why: most rag failures are retrieval failures, so whoever can debug retrieval gets paid

• learn: the agent loop, tool descriptions, state, retries, and when an agent is the wrong call

• practice: build one agent with no framework at all, just the api, 3 tools and a while loop

• why: a chain of 3 fixed calls beats an agent that might make 3 calls, and knowing which one you need is the senior part

• learn: docker, background jobs, auth, rate limits, tracing with langfuse, caching, cost control

• practice: containerize your rag app with a vector db and redis, then put a hard daily spend cap on it

• why: this is where most people stall, they can demo but they can't survive real traffic at 2am

• learn: product engineering, applied ml, or business automation

• practice: ship 2-3 projects a stranger can open and use without you explaining anything

• why: six months makes you dangerous in one direction, not average in three

X 官方翻译

• 学习：Python、Git、终端、HTTP和JSON、基础SQL、FastAPI

• 练习：构建一个CLI工具，调用公共API并将干净的JSON写入磁盘

• 为什么：AI工程首先是软件工程，下面的每个阶段都假设你能交付一个可工作的端点

• 学习：提示工程、用Pydantic实现结构化输出、工具调用、流式传输、对话状态、令牌成本

• 练习：构建一个发票解析器，返回一个类型化的Python对象，然后给模型提供3个工具，让它自己选择

• 为什么：这就是实际的工作，大多数人直接跳过它去搞代理

• 学习：嵌入、块分割、向量存储、元数据过滤、重排序

• 练习：摄入20个PDF，并交付一个端点，从前5个块中返回带引用的答案

• 为什么：大多数RAG失败都是检索失败，所以谁能调试检索，谁就能拿到报酬

• 学习：代理循环、工具描述、状态、重试，以及何时不该用代理

• 练习：完全不用框架构建一个代理，就用API、3个工具和一个while循环

• 为什么：3个固定调用的链条胜过一个可能调用3次的代理，知道用哪个才是资深水平

• 学习：Docker、后台任务、认证、速率限制、用Langfuse追踪、缓存、成本控制

• 练习：用向量数据库和Redis容器化你的RAG应用，然后给它设置一个严格的每日花费上限

• 为什么：大多数人卡在这里，他们能做演示，但无法在凌晨2点承受真实流量

• 学习：产品工程、应用机器学习，或业务自动化

• 练习：交付2-3个项目，让陌生人无需你解释就能打开并使用

• 为什么：六个月让你在一个方向上变得危险，而不是在三个方向上平庸

图片 / 媒体

梗解释 / 点评

推文截图