Loading…
Course dashboard
Popular lessons first — each course includes modules, materials, and a ready-made timeline. Select one to create a classroom.
Series appear first as cards — then individual courses. Search or filter by subject, series, grade, or access.
52 results
Subject
Series
Grade
Access
Course series
Project I of the EdUHK MSc AIDCEC programme. A guided, multi-part path for building a professional chatbot — from foundations to tools, retrieval, and evaluation.
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.
Course series
Ten three-hour lectures from production conversational LLM systems to advanced agent architectures — bilingual catalog entries for en and zh-CN. Reuses and deepens themes from agentic-ai-10.
A complete 6-hour, pick-up-and-teach unit on RAG, retrieval, agent memory, and sharing student chatbot works — with warm-ups, labs, a quiz battle, breaks, and reflection.
Explore organelles, prokaryotes vs eukaryotes, and cell structure with a live tutor and organelle quiz.
Vectors, matrices, and transformations — with a document tutor and auto-generated study guide.
Craft strong thesis statements and structure essays with a writing coach and peer-review checklist.
Passage strategies, timing tips, and practice comprehension — ready for test day.
Variables, control flow, and functions — with tutor, quiz, and study guide for beginners.
A 4-hour course for teachers and developers: understand MCP architecture, build and validate tool manifests, run interactive labs, and publish a classroom MCP tool via VibeKoala.
A short lab on token-effective classroom animation: presets, chunk reveal, concept pipelines, and safe-motion rules — authored as UiPageManifest, not free GSAP.
3-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）。
Precision lexis, collocations, and paraphrase drills for Band 8–9 lexical resource — with typing practice, flashcards, mind map, quiz battle, and slides.
3-hour foundation: production conversational LLM apps, prompt construction, context windows, token budgets, and stateful multi-turn layers — with breaks.
3 小时基础：生产级对话式 LLM、提示词构建、上下文窗口、token 预算与有状态多轮层（含休息）。
3-hour agentic baseline: schema-constrained JSON, structured outputs, and safe tool calling for downstream APIs — with breaks.
3 小时 Agentic 基线：schema 约束 JSON、结构化输出与安全工具调用（含休息）。
3-hour reasoning lab: Reflection, ReAct, and Plan-and-Solve loops for task decomposition and self-correction — with breaks.
3 小时推理实验：Reflection、ReAct 与 Plan-and-Solve 任务分解与自我纠错（含休息）。
3-hour graph lab: nodes, edges, conditional routing, and deterministic state machines that prevent runaway agents — with breaks.
3 小时图工作流：节点、边、条件路由与防止失控的确定性状态机（含休息）。
3-hour multi-agent lab: specialist roles, shared state, protocols, and supervisor orchestration — with breaks.
3 小时多智能体：专长角色、共享状态、通信协议与 supervisor 编排（含休息）。
3-hour MCP & Skills lab: Host/Client/Server, tools/resources/prompts, and Agent Skills (SKILL.md) — with breaks.
3 小时 MCP 与 Skills：Host/Client/Server、工具/资源/提示与 Agent Skills（含休息）。
3-hour vibe-coding lab: AI-native SDLC with Claude Code / Cline-style agents under human-in-the-loop — with breaks.
3 小时氛围编程：人机协同下的 AI 原生开发生命周期（含休息）。
3-hour security lab: red-team workflows, prompt injection, exfiltration, tool hijacking, and privilege escalation — with breaks.
3 小时安全实验：红队流程、提示注入、外泄、工具劫持与权限提升（含休息）。
3-hour production lab: multi-layer memory, durable state backends, and eval pipelines for accuracy, drift, and performance — with breaks.
3 小时生产工程：多层记忆、持久状态后端与准确率/漂移/性能评测流水线（含休息）。
3-hour governance + capstone: runtime guardrails, cost/scope ceilings, and student-defined project demos (covers syllabus weeks 11–12) — with breaks.
3 小时治理与综合项目：运行时护栏、成本/范围上限与学生自定项目演示（覆盖大纲第 11–12 周）（含休息）。
Course dashboard
Popular lessons first — each course includes modules, materials, and a ready-made timeline. Select one to create a classroom.
49 results
Subject
Series
Grade
Access
Series appear first as cards — then individual courses. Search or filter by subject, series, grade, or access.
Course series
Project I of the EdUHK MSc AIDCEC programme. A guided, multi-part path for building a professional chatbot — from foundations to tools, retrieval, and evaluation.
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.
Course series
Ten three-hour lectures from production conversational LLM systems to advanced agent architectures — bilingual catalog entries for en and zh-CN. Reuses and deepens themes from agentic-ai-10.
A complete 6-hour, pick-up-and-teach unit on RAG, retrieval, agent memory, and sharing student chatbot works — with warm-ups, labs, a quiz battle, breaks, and reflection.
Explore organelles, prokaryotes vs eukaryotes, and cell structure with a live tutor and organelle quiz.
Vectors, matrices, and transformations — with a document tutor and auto-generated study guide.
Craft strong thesis statements and structure essays with a writing coach and peer-review checklist.
Passage strategies, timing tips, and practice comprehension — ready for test day.
Variables, control flow, and functions — with tutor, quiz, and study guide for beginners.
A 4-hour course for teachers and developers: understand MCP architecture, build and validate tool manifests, run interactive labs, and publish a classroom MCP tool via VibeKoala.
A short lab on token-effective classroom animation: presets, chunk reveal, concept pipelines, and safe-motion rules — authored as UiPageManifest, not free GSAP.
3-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）。
Precision lexis, collocations, and paraphrase drills for Band 8–9 lexical resource — with typing practice, flashcards, mind map, quiz battle, and slides.
3-hour foundation: production conversational LLM apps, prompt construction, context windows, token budgets, and stateful multi-turn layers — with breaks.
3 小时基础：生产级对话式 LLM、提示词构建、上下文窗口、token 预算与有状态多轮层（含休息）。
3-hour agentic baseline: schema-constrained JSON, structured outputs, and safe tool calling for downstream APIs — with breaks.
3 小时 Agentic 基线：schema 约束 JSON、结构化输出与安全工具调用（含休息）。
3-hour reasoning lab: Reflection, ReAct, and Plan-and-Solve loops for task decomposition and self-correction — with breaks.
3 小时推理实验：Reflection、ReAct 与 Plan-and-Solve 任务分解与自我纠错（含休息）。
3-hour graph lab: nodes, edges, conditional routing, and deterministic state machines that prevent runaway agents — with breaks.
3 小时图工作流：节点、边、条件路由与防止失控的确定性状态机（含休息）。
3-hour multi-agent lab: specialist roles, shared state, protocols, and supervisor orchestration — with breaks.
3 小时多智能体：专长角色、共享状态、通信协议与 supervisor 编排（含休息）。
3-hour MCP & Skills lab: Host/Client/Server, tools/resources/prompts, and Agent Skills (SKILL.md) — with breaks.
3 小时 MCP 与 Skills：Host/Client/Server、工具/资源/提示与 Agent Skills（含休息）。
3-hour vibe-coding lab: AI-native SDLC with Claude Code / Cline-style agents under human-in-the-loop — with breaks.
3 小时氛围编程：人机协同下的 AI 原生开发生命周期（含休息）。
3-hour security lab: red-team workflows, prompt injection, exfiltration, tool hijacking, and privilege escalation — with breaks.
3 小时安全实验：红队流程、提示注入、外泄、工具劫持与权限提升（含休息）。
3-hour production lab: multi-layer memory, durable state backends, and eval pipelines for accuracy, drift, and performance — with breaks.
3 小时生产工程：多层记忆、持久状态后端与准确率/漂移/性能评测流水线（含休息）。
3-hour governance + capstone: runtime guardrails, cost/scope ceilings, and student-defined project demos (covers syllabus weeks 11–12) — with breaks.
3 小时治理与综合项目：运行时护栏、成本/范围上限与学生自定项目演示（覆盖大纲第 11–12 周）（含休息）。