Use code SAVE 5 for 5% off on Physical Book !

How AI Really Works: From Prompt to Token

A technical deep-dive into what actually happens between typing a prompt into an AI system and getting a response back.

From the 70-year history of chatbots through tokenization, embeddings, transformers, and how a base model becomes a helpful assistant.

Adult Learning
12:15:00
1001 students
Michael Williams
Learning Objectives

  • Understand what a large language model actually is and how it differs from earlier chatbots
  • Trace the technical lineage from statistical language modelling to modern transformers
  • Explain tokenization, embeddings, and self-attention in plain language
  • Describe how a base model becomes an instruction-following assistant via fine-tuning, RLHF, and tool calling

Prerequisites

No formal prerequisites — this course is written for anyone curious about how AI actually works.

  • Helpful, but not required: comfort reading basic Python code (each module includes short, real code examples)
  • Helpful, but not required: general familiarity with using an AI chatbot like Claude or ChatGPT

Course Content
Module 1: The Origins of AI & Chatbots

Before large language models, six decades of rule-based chatbots and one landmark experiment in information theory set the stage for everything that followed.

Large Language Models (LLM) - How they Work
Video 0:05:35
Enroll to Access
1.1 What Is a Language Model, Really?
Reading 0:18:00
Enroll to Access
1.2 Claude Shannon and the Predictability of Language
Reading 0:18:00
Enroll to Access
1.3 The Rule-Based Chatbot Era (1966–2001)
Reading 0:18:00
Enroll to Access
1.4 Module 1 Quiz — Origins of AI & Chatbots
Quiz 0:15:00
Enroll to Access
Module 2: How Neural Networks Learn

Neural networks are the engine inside every modern AI system. This module traces the idea from a 1943 theoretical paper, through a hyped-up 1958 machine, a near-fatal 1969 critique, and the 1986 breakthrough that made today's deep learning possible.

A Neural Network: What it is.
Video 0:19:00
Enroll to Access
2.1 What Is a Neural Network?
Reading 0:15:00
Enroll to Access
2.2 From McCulloch-Pitts to the Perceptron (1943–1958)
Reading 0:15:00
Enroll to Access
PT2: Gradient descent, how neural networks learn | Deep Learning
Video 0:20:35
Enroll to Access
2.3 The XOR Problem and the Rise of Backpropagation (1969–1986)
Reading 0:15:00
Enroll to Access
PT3:Deep Learning | Backpropagation, intuitively
Video 0:13:00
Enroll to Access
2.4 Module 2 Quiz — How Neural Networks Learn
Quiz 0:15:00
Enroll to Access
Module 3: Tokenization & Embeddings

Before a neural network can process a prompt, that prompt has to become numbers. This module covers how text is split into tokens, where the byte pair encoding algorithm actually came from, and how embeddings give a model a numeric sense of meaning.

3.1 What Is Tokenization?
Reading 0:15:00
Enroll to Access
3.2 Byte Pair Encoding: From Compression Trick to Language Vocabulary
Reading 0:15:00
Enroll to Access
3.3 Word Embeddings and the Geometry of Meaning
Reading 0:15:00
Enroll to Access
Embeddings
Video 0:08:40
Enroll to Access
3.4 Module 3 Quiz — Tokenization & Embeddings
Quiz 0:15:00
Enroll to Access
Module 4: Inside the Transformer

The Transformer architecture powers essentially every modern large language model. This module covers where it came from, how self-attention lets tokens exchange information, how a model actually chooses its next word, and how it all fits inside a context window.

Transformers
Video 0:30:00
Enroll to Access
4.1 The Transformer Architecture: An Overview
Reading 0:15:00
Enroll to Access
4.2 Self-Attention: How Tokens Talk to Each Other
Reading 0:18:00
Enroll to Access
4.3 From Logits to Language: Softmax, Temperature, and Sampling
Reading 0:18:00
Enroll to Access
4.4 Context Windows and the Full Picture
Reading 0:15:00
Enroll to Access
4.5 Module 4 Quiz — Inside the Transformer
Quiz 0:15:00
Enroll to Access
Module 5: From Autocomplete to Assistant

Everything so far describes a base model: a very capable next-token predictor with no particular tendency to be helpful. This final content module covers fine-tuning, reinforcement learning from human feedback, and tool calling — the steps that turn that base model into an assistant.

5.1 Pretraining, Fine-Tuning, and the Base Model
Reading 0:15:00
Enroll to Access
5.2 Reinforcement Learning from Human Feedback (RLHF)
Reading 0:18:00
Enroll to Access
RLHF
Video 0:12:00
Enroll to Access
5.3 Tool Calling: Letting Models Act in the World
Reading 0:18:00
Enroll to Access
Tool Calling
Video 0:05:00
Enroll to Access
5.4 Module 5 Quiz — From Autocomplete to Assistant
Quiz 0:15:00
Enroll to Access
Module 6: Course Assignment

The capstone for this course: demonstrate, in your own words, that you can trace a prompt through the entire pipeline covered across Modules 1 through 5.

Large Language Models (Revision)
Video 1:00:00
Enroll to Access
6.1 Capstone Assignment: Trace a Prompt Through the Full Pipeline
Assignment 0:45:00
Enroll to Access

Premium Content Preview

This course includes:

  • 5 interactive quizzes
  • 31 comprehensive lessons
  • Multiple lesson formats (videos, readings, activities)
  • Progress tracking and certificates

Enroll now to access all content!

Course Information
Level: Adult Learning
Duration: 12:15:00
Students: 1001
Modules: 6
Lessons: 31
Quizzes: 5

£29.99/month
or £249.97/year
Courses over 30 hours, 7-day money-back guarantee
Need Help with This Course?

Have a question about How AI Really Works: From Prompt to Token? Message Michael Williams directly and we'll get back to you.

Platform Assistant

Sign up free to unlock our AI assistant!

Welcome! Sign up free to unlock our full AI assistant!

Free Sign-up Benefits:
AI-powered help, course recommendations, progress tracking
Processing...