Loading…
Course series
Ten three-hour lectures (with breaks) from Agile/Scrum through RAG, agents, MCP, eval, security, and governance — bilingual catalog entries for en and zh-CN.
20 courses in this series
Lecture accents
Sign in to create a classroom for this series and load lectures one at a time.
Sign in3-hour opener: Scrum accountabilities, events, artifacts, AI usage contract, and a team backlog workshop — with breaks.
3 小时开篇：Scrum 问责、事件、工件、AI 使用契约与组队待办工作坊（含休息）。
3-hour unit on Chat Completions roles, conversation state, context budgets, and a live chat UI lab — with breaks.
3 小时单元：Chat Completions 角色、对话状态、上下文预算与聊天 UI 实验（含休息）。
3-hour engineering lab: JSON Schema structured outputs vs tool calling, TypeScript types, and Jest tests — with breaks.
3 小时工程实验：JSON Schema 结构化输出 vs 工具调用、TypeScript 类型与 Jest 测试（含休息）。
3-hour backend and deploy lab: env vars, CORS, reverse proxy, Docker/Nginx paths — with breaks.
3 小时后端与部署实验：环境变量、CORS、反向代理、Docker/Nginx 路径（含休息）。
3-hour RAG lab: chunking, retrieval metrics first, then generation — with optional agentic-RAG peek and breaks.
3 小时 RAG 实验：分块、先测检索再测生成 — 含选修 Agentic RAG 简介与休息。
3-hour agents lab: graphs, checkpoints, supervisor limits, and why MemorySaver is not production — with breaks.
3 小时智能体实验：图、检查点、Supervisor 上限，以及为何 MemorySaver 不宜生产（含休息）。
3-hour MCP and skills lab: classroom baseline on 2025-11-25, RC awareness for 2026-07-28, and safe vibe coding — with breaks.
3 小时 MCP 与 Skills 实验：课堂实现跟 2025-11-25，口头介绍 2026-07-28 RC，以及安全 Vibe Coding（含休息）。
3-hour eval lab: offline → online → calibration, RAGAS-style metrics, and LangSmith-style traces — with breaks.
3 小时评估实验：离线→在线→校准、RAGAS 类指标与 LangSmith 类轨迹（含休息）。
3-hour security lab: OWASP LLM Top 10 2025, prompt injection drills, and auth basics — with breaks.
3 小时安全实验：OWASP LLM Top 10 2025、提示注入演练与认证基础（含休息）。
3-hour capstone: cost attribution (not hard dollar stops), AI law/ethics for teaching contexts, and final demos — with breaks.
3 小时期末：成本归因（非美元硬停）、教学场景 AI 法律伦理与期末演示（含休息）。