Stanford University CS146S: The Modern Software Developer
# The Modern Software Developer > 基于 Stanford University CS146S: The Modern Software Developer **[English Version](README_EN.md)** | **[日本語版](README_JA.md)** | [学习检查清单](CHECKLIST.md) | [资源汇总](resources/README.md) --- ## 课程简介 近年来,大语言模型为软件开发引入了革命性的新范式。传统的软件开发生命周期正在各个阶段被 AI 自动化所改变,这引发了一个问题:下一代软件工程师应该如何工作? 本课程将展示现代 AI 工具如何改变软件开发——它降低了应用开发的门槛,但复杂应用仍需要工程师的判断。本课程涵盖了传统软件工程挑战背后的理论,以及当今解决这些问题的前沿 AI 工具。 > **重要**:这**不是一门 "vibe coding" 课程**。你不能盲目相信 AI 的输出。**Human-agent engineering** 才是核心——人类工程师作为 AI 的管理者和决策者,需要阅读和审查大量代码,理解什么是优秀的软件。 --- ## 课程概览 | 章节 | 主题 | 学习资料 | 幻灯片 | |------|------|----------|--------| | [第 1 章](days/chapter1.md) | 编程 LLM 和 AI 开发入门 | [资料](days/chapter1.md) | [Lecture 1](/slides/week1-lecture1-introduction.pdf) / [Lecture 2](/slides/week1-lecture2-power-prompting.pdf) | | [第 2 章](days/chapter2.md) | 编程智能体的架构 | [资料](days/chapter2.md) | [Lecture 1](/slides/week2-lecture1-coding-agent-scratch.pdf) / [Lecture 2](/slides/week2-lecture2-mcp-server.pdf) | | [第 3 章](days/chapter3.md) | AI 集成开发环境 | [资料](days/chapter3.md) | [Lecture 1](/slides/week3-lecture1-ide-setup.pdf) / [Lecture 2](/slides/week3-lecture2-cognition.pdf) | | [第 4 章](days/chapter4.md) | 编程智能体模式 | [资料](days/chapter4.md) | [Lecture 1](/slides/week4-lecture1-agent-manager.pdf) / [Lecture 2](/slides/week4-lecture2-claude-code.pdf) | | [第 5 章](days/chapter5.md) | 现代终端 | [资料](days/chapter5.md) | [PDF](/slides/week5-lecture1-ai-developer-product.pdf) | | [第 6 章](days/chapter6.md) | AI 测试与安全 | [资料](days/chapter6.md) | [PDF](/slides/week6-lecture1-ai-qa-sast-dast.pdf) | | [第 7 章](days/chapter7.md) | 现代软件支持 | [资料](days/chapter7.md) | [PDF](/slides/week7-lecture1-code-review.pdf) | | [第 8 章](days/chapter8.md) | 自动化 UI 和应用构建 | [资料](days/chapter8.md) | [Lecture 1](/slides/week8-lecture1-end-to-end-apps.pdf) / [Lecture 2](/slides/week8-lecture2-vercel.pdf) | | [第 9 章](days/chapter9.md) | Agent 部署后运维 | [资料](days/chapter9.md) | [PDF](/slides/week9-lecture1-incident-response.pdf) | | [第 10 章](days/chapter10.md
Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.