AI Fundamentals Tutorials

Table of Contents +

Welcome to the AI Fundamentals tutorials. This course starts from zero, so even if words like model, token, prompt, LLM, RAG, and agent feel completely new, that is fine.

We will not assume you already know AI. We will explain each word first, then slowly connect it to real apps.

Start from zero

First we explain the simple meaning of AI words before using them in bigger ideas.

Connect the pieces

You will see how model, prompt, token, context, RAG, agents, MCP, and backend fit inside one app.

End with app thinking

By the end, you will understand the shape of a small LLM app.

🌍 Names You Will Recognize

You may already know some AI tools and model names.

Chat apps

ChatGPT, Claude, and Gemini are products where you type prompts and receive AI answers.

Model names

GPT, Claude, Gemini, Llama, Gemma, Mistral, and Qwen are model families or model-backed names you may hear.

Developer tools

Ollama, Copilot-style assistants, RAG apps, and agents are ways developers use models inside real software.

Here is the course path in one picture:

AI basics

Models and LLMs

Prompts and tokens

Limits and risks

RAG and agents

First LLM app

🎯 What You Will Learn

In this AI course, you will learn:

Part What you will understand
AI basics What AI means through examples like YouTube recommendations, spam detection, and chatbots.
AI family What machine learning, deep learning, and generative AI mean.
Models What a model is and why people keep talking about models.
LLMs What an LLM is by separating the chat screen, app backend, and model.
Core words What tokens, prompts, context, inference, and temperature mean.
Risks Why AI can give wrong answers, even when it sounds confident.
App parts What prompting, embeddings, RAG, agents, MCP, tools, and memory mean in normal language.
First app How a small AI app works from screen to backend to model.

📚 Topics List

Follow these topics in order. Each one builds the vocabulary for the next one:

  1. 🧠 Introduction to AI
  2. 🧩 AI Models and Foundation Models
  3. 💬 AI Large Language Models
  4. ✍️ AI Prompting Basics
  5. 🔁 AI Prompt Improvement Loop
  6. 🔤 AI Tokens and Tokenization
  7. 📚 AI How LLMs Learn
  8. ⚙️ AI Transformers and Attention
  9. 🧾 AI Context Windows
  10. ⚡ AI Inference and Generation Settings
  11. ⚠️ AI Hallucinations
  12. ⏳ AI Model Knowledge and Cutoff
  13. 🔎 AI Embeddings and Semantic Search
  14. 📚 AI RAG Basics
  15. ⚖️ AI LLMs vs Traditional Software
  16. 🏗️ AI Application Architecture
  17. 🧭 AI Models vs AI Applications
  18. 🧭 AI Agents Basics
  19. 🔌 AI MCP Basics
  20. ☁️ AI Cloud vs Local Models
  21. 📘 AI Common Generative AI Terms
  22. 🚀 AI Build Your First LLM Application

🧭 How the Course Is Connected

This course is not only definitions.

  • 🧠 First, we explain AI using normal examples.
  • 🧩 Then we explain the basic building blocks and prompting.
  • ⚠️ After that, we explain the problems, like wrong answers and missing knowledge.
  • 🔎 Then we show how embeddings and RAG help apps answer from documents.
  • 🏗️ Then we explain app architecture, agents, MCP, and deployment choices.
  • 🚀 Finally, we build the shape of a small AI app so the full picture becomes clear.

🛤️ How to Use These Tutorials

  • Start from the first lesson. Do not jump directly to RAG or agents.
  • Read slowly. Many AI words sound heavy at first, but most have simple meanings.
  • Keep a small notes file. Write the term and one plain meaning beside it.
  • If one lesson feels hard, reread the examples before moving forward.

✅ Prerequisites

You do not need machine learning math.

You do not need to know how AI models are trained.

Basic programming knowledge will help near the end, but the early lessons explain the ideas from the beginning.

🚀 Getting Started

Start with Introduction to AI. We will begin with the big picture, then slowly move toward real LLM applications.

Next Introduction to AI