Generative AI Course Index
Students Notes Website → Students
How to use this index
Each row has a Topic and Description. Copy both into AI to generate a missing note:
"Write an Obsidian markdown note for a beginner AI course. Topic: [Topic]. Cover: [Description]. Use callouts, tables, simple analogies — curious senior explaining to school-passed non-tech students."
Module 1 — AI Landscape & Transformation
| Notes | Topic | Description |
|---|---|---|
| M0 - Second brain setup | Second brain setup | Obsidian + GitHub + Vercel digital garden setup |
| M1-A - The Intelligence Stack | Intelligence stack | AI layers from rules to agents |
| M1-B - Prompting as a Skill | Prompting as a skill | Precision, context, specification mindset |
| M1-C - Where AI Actually Matters | Where AI matters | High-leverage use cases vs hype |
Module 2 — LLM Fundamentals
| Notes | Topic | Description |
|---|---|---|
| M2-A - What is happening inside AI | Inside AI | Next-token prediction, patterns not facts |
| M2-B - How AI generates answers | How AI answers | Generation loop and what you control |
| M2-C - Why AI makes mistakes | AI mistakes | Hallucination, limits, verification |
| M2-D - How to use AI correctly | Use AI correctly | Practical operating rules |
| M2-E - Final mental model | Module 2 summary | One-page mental model |
Module 3 — Advanced Prompt Engineering
| Notes | Topic | Description |
|---|---|---|
| M3-A What is Prompt | What is a prompt | Components and prompting techniques |
| M3-B Role based prompting | Role-based prompting | Persona and expert roles |
| M3-C Prompt Chaining | Prompt chaining | Multi-step prompt flows |
| (Assignment 1)Prompt designer Extenstion | Assignment — Prompt designer | Custom template + 11 questions |
| (Assignment 2 ) Linkedin evaluation with engineered prompt | Assignment — LinkedIn | Meta-prompt profile review |
Module 4 — Prompt Systems & Automation
| Notes | Topic | Description |
|---|---|---|
| M4-A — Reusable Prompt Systems | Reusable prompt systems | Save templates as .md files for consistent output |
| M4-B — Prompt-Based Automation | Prompt automation | Chain prompts into repeat workflows |
| Ruleset Prompt | AI response ruleset | System prompt rules for behaviour control |
Module 5 — Multimodal AI Systems
| Notes | Topic | Description |
|---|---|---|
| M5-A — Text Image and Video AI | Multimodal AI | Text, image, video tools and backends |
| M5-B — AI Content Pipelines | Content pipelines | Factory-line content workflows |
| M5-C — Cross-Modal Workflows | Cross-modal workflows | Handoffs between text, image, video |
| Prompt Templates | Image prompt templates | Poster and photoshoot practical prompts |
| (Assignment 3) Google AI for marketing | Assignment — Pomelli | Marketing campaign with Google AI |
| (Assignment 4) Build and deploy a landing page website | Assignment — Landing page | HTML/CSS site on Netlify |
Module 6 — AI Productivity Systems
| Notes | Topic | Description |
|---|---|---|
| M6-A — AI for Decision-Making and Business Productivity | AI decision-making | Prepare vs judge, hidden taxes, human-in-the-loop |
| M6-B — AI-Driven Workflows and Tools | AI workflows | Workflow anatomy and tool landscape |
| (Assignment) topics to learn for module 6 | Assignment — Module 6 review | Written answers on AI limits |
Module 7 — Retrieval-Augmented Generation (RAG)
| Notes | Topic | Description |
|---|---|---|
| M7-A — What is RAG | What is RAG | Open-book exam analogy, why ChatGPT alone fails |
| M7-B — How RAG Works Behind the Scenes | RAG backend | Chunks, embeddings, vector search |
| M7-C — RAG with NotebookLM | NotebookLM practice | Hands-on document chat |
| (Assignment) Solve Questions | Assignment — Concept Q&A | APIs, RAG, databases, frontend/backend |
Module 8 — AI Knowledge Assistants
| Notes | Topic | Description |
|---|---|---|
| M8-A — Document-Based AI Assistants | Document assistants | Study bot design with RAG + personality |
| M8-B — Internal Knowledge Systems | Internal knowledge | Team wikis and SOP search |
Module 9 — AI Agents & Capabilities
| Notes | Topic | Description |
|---|---|---|
| M9-A — What Are AI Agents | What are agents | Chatbot vs agent, tools, loops |
| M9-B — Memory Planning and Execution | Memory, plan, execute | Three engine parts of agents |
| M9-C — Autonomous Workflows | Autonomous workflows | Triggers, autonomy levels |
| Open claw | OpenClaw (bonus) | Markdown memory + messaging gateway |
Module 10 — Multi-Agent Workflows
| Notes | Topic | Description |
|---|---|---|
| M10-A — When One Agent Is Not Enough | Multi-agent why | Film crew analogy, collaboration patterns |
| M10-B — Task Distribution and Orchestration | Orchestration | Task graphs, parallel vs sequential |
Module 11 — Agent Frameworks (Intro)
| Notes | Topic | Description |
|---|---|---|
| M11-A — CrewAI How It Works | CrewAI | Agents, tasks, crews, backend loop |
| M11-B — AutoGen Introduction | AutoGen | Group-chat agents vs CrewAI |
Bonus — Module 12+ preview
| Notes | Topic | Description |
|---|---|---|
| N8N install | n8n install | Visual automation setup |
| Whatsapp analytics | WhatsApp analytics | Streamlit chat export project |