Loading…
For tutors
Ready-made courses with multiple activities, shared materials, and worksheets — load a full lesson into your classroom in one click.
Students join with a passcode. You stay in control with monitoring and outcome-ready templates.
Spotlighted
Flip through the stack, pick a course, then open it to create your classroom.
Selected: AI Memory Systems
Use this course38 results
Subject
Series
Grade
Access
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.
A 155-minute class: Agile, waterfall vs the loop, Git as a code-management framework, the chatbot stack, and an in-class EdUHK GenAI vibe lab.
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。
Precision lexis, collocations, and paraphrase drills for Band 8–9 lexical resource — with typing practice, flashcards, mind map, quiz battle, and slides.
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: coding agents ship faster while humans review and approve every change under HITL — with breaks.
3 小时氛围编程：编码智能体加速交付，人类在 HITL 下审查并批准每一处变更（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 lab: runtime guardrails, cost/scope ceilings, and HK PCPD-aware controls — with breaks.
3 小时治理实验：运行时护栏、成本/范围上限与香港 PCPD 感知控制（含休息）。
3-hour production gate: deploy, harden, and evaluate a live AI system against agreed performance, safety, and reliability criteria — with breaks.
3 小时生产关卡：部署、加固并评测线上 AI 系统，对照约定的性能、安全与可靠性标准（含休息）。
3-hour decision gate: executive panel defence, governance approval, and operational handover with a complete documentation pack — with breaks.
3 小时决策关卡：高管答辩、治理批准与带完整文档包的运营移交（含休息）。
A short walkthrough of every standardized React envelope layout — pick a shape for the teaching beat; type and gap stay frozen.
Simplified Chinese walkthrough of every standardized React envelope layout — pick a shape for the teaching beat; type and gap stay frozen.