LEARN

从这里开始学习Start Learning Here

这里是上课入口：按阶段进入课程、教程和项目。想先看完整能力全景，请去系统路线图。This is the classroom entrance: follow stages into lessons, tutorials, and projects. Use the roadmap for the full capability map.

LEARN VS ROADMAP

学习路径负责“下一步学什么”；系统路线图负责“为什么这些能力属于 FDE”。 The learning path answers what to study next; the roadmap explains why these capabilities belong to FDE.

查看系统路线图

阶段式课程入口

先理解 FDEUnderstand FDE First

明确前线部署工程师做什么、不做什么，以及为什么所有训练都围绕 AI 工具交付。Clarify what a Forward Deployed Engineer does and does not do, and why training centers on AI-tool delivery.

AI 工具工作流AI Tool Workflow

用 Codex、Claude Code、Antigravity、Cursor 理解项目、改页面、跑构建、查错误。Use Codex, Claude Code, Antigravity, and Cursor to inspect projects, edit pages, run builds, and debug errors.

从需求到 DemoRequirement to Demo

把企业需求写成 AI 工具任务卡、Prompt、页面结构和验收标准。Turn business needs into AI-tool task briefs, prompts, page structures, and acceptance checks.

Agent 工作流Agent Workflow

用 AI 工具画流程、生成最小 Demo、补测试，并保留人审、权限和审计边界。Use AI tools to map flows, generate minimal demos, add tests, and preserve human review, access, and audit boundaries.

部署、评估与交付Deploy, Evaluate, Deliver

完成可访问 URL、日志检查、回滚说明、评估报告和交付文档。Ship accessible URLs, log checks, rollback notes, evaluation reports, and delivery documents.

Soft Stack 与行业案例Soft Stack and Industry Cases

训练 Diagnostic Mindset，再进入跨境电商、文旅和企业诊断案例。Train the Diagnostic Mindset, then move into commerce, tourism, and enterprise diagnosis cases.

FDE 职业进阶FDE Career Track

把公开 FDE 面试准备资料重组为 AI 工具协作开发、Agent 系统设计、技术表达和项目复盘。Reframe public FDE preparation into AI-assisted coding, agent system design, technical communication, and project review.

学习工具箱

项目题库Project Bank

把课程能力落到 8 周项目任务、结业作品和验收清单里。Turn course skills into 8-week project tasks, capstones, and acceptance checks.

课件与资源Resources

需求澄清表、Prompt、测试清单、演示脚本和复盘材料。Clarification forms, prompts, test checklists, demo scripts, and review materials.

交付模板Templates

PRD、SOW、ADR、Runbook 和评估 Rubric 等可复用交付资产。Reusable delivery assets such as PRDs, SOWs, ADRs, runbooks, and rubrics.

评分体系Assessment

用作品、工具轨迹、交付文档和边界意识判断学习成果。Evaluate outcomes through artifacts, tool traces, delivery docs, and boundary awareness.

FDE 职业进阶

AI 工具协作开发AI-Assisted Vibe Coding

从逐行写代码转向描述意图、拆任务、审输出、跑验证，用 Codex、Claude Code、Cursor 和 Antigravity 交付 Demo。Move from writing every line to framing intent, decomposing tasks, reviewing output, and validating demos with AI coding tools.

生产级 Agent 系统设计Production Agentic System Design

学习编排、结构化输出、上下文压缩、RAG、工具调用、护栏、成本控制和系统化评估。Study orchestration, structured output, context compression, RAG, tool calls, guardrails, cost control, and systematic evaluation.

DSA Lite 技术表达DSA Lite for Technical Communication

保留算法模式训练，但不把 FDE FAN 做成刷题站：目标是能讲清复杂度、边界条件和方案权衡。Keep algorithm patterns as communication training, not a problem-grinding track: explain complexity, edge cases, and tradeoffs.

Mock Interview 与项目复盘Mock Interview and Project Review

用真实项目做 30 分钟演示、Prompt + 输出审查、失败诊断和 STAR 复盘。Use real projects for 30-minute demos, prompt-output review, failure diagnosis, and STAR retrospectives.

8 周训练路径

01 FDE 岗位认知 Role map 02 需求拆解与 Prompt Prompt 03 AI 生成前端 UI demo 04 AI 编程工具实战 Coding 05 Agent 工作流 Workflow 06 部署与交付 Deploy 07 综合项目冲刺 Capstone 08 结业路演与分层 Demo day

12 篇基础教程

FDE 岗位边界FDE Role Boundaries 理解 AI-FDE 如何在业务意图、上下文、数据权限、Agent、前端 Demo、评估和交付文档之间承担轻量工程交付。 Understand how AI-FDE connects intent, context, data access, agents, demos, evaluation, and delivery docs. HTML/CSS 与页面结构HTML/CSS and Page Structure 掌握工具页、报告页、表单页和后台页最常见的结构。 Learn common structures for tools, reports, forms, and dashboards. JavaScript、React 与交互状态JavaScript, React, and UI State 学习输入、筛选、异步请求、加载状态和错误提示。 Learn input, filters, async requests, loading states, and error feedback. 从本地项目到线上 URLFrom Local Project to Production URL 理解构建、托管平台、环境变量、域名、日志、回滚和交付验收。 Understand build, hosting, env vars, domains, logs, rollback, and delivery acceptance. 需求拆解与验收标准Requirement Breakdown and Acceptance 把模糊需求拆成页面目标、输入输出、流程、边界和验收标准。 Turn vague needs into goals, inputs, outputs, flows, boundaries, and acceptance criteria. Prompt 到前端 DemoPrompt to Front-End Demo 使用结构化 Prompt 生成页面，并对 AI 输出做审查和迭代。 Use structured prompts to generate pages, then review and iterate the output. Agent 基础：状态、工具与记忆Agent Basics: State, Tools, and Memory 理解 Agent 如何读取上下文、调用工具、保存状态和返回结果。 Understand context, tool calls, state persistence, and result generation. 企业 AI 转型诊断 Agent 拆解Enterprise Diagnosis Agent Breakdown 拆解 diagnosis 工具的会话、画像抽取、追问、报告生成和历史记录。 Break down session, profile extraction, follow-up, report generation, and history. 跨境电商 AI 场景地图Cross-Border AI Scenario Map 基于 OPC 跨境电商 AI 工具矩阵，识别选品、POD、内容、投放、达人、ERP、本地化、合规、金融和客服中的 AI 试点。 Use the OPC commerce AI matrix to identify pilots across products, POD, content, ads, creators, ERP, localization, compliance, finance, and support. 上线元数据与链接预览Launch Metadata and Link Preview 部署完成后，检查标题、描述、OG 图和社交平台链接预览。 After deployment, check title, description, OG image, and social link previews. 交付文档与演示脚本Delivery Docs and Demo Script 用 README、测试清单、演示脚本和复盘报告完成交付闭环。 Close delivery with README, test checklist, demo script, and retrospective. 作品集与结业路演Portfolio and Demo Day 把项目整理成可展示的作品集，并按 A/B/C/D 标准进行评估。 Package projects into a portfolio and assess them with A/B/C/D levels.