Skip to main content

Menu

System onlineAI Tutorials / 2026

AI Tutorials
Knowledge search

Recent · Popular · Tutorials

  • Artificial Intelligence42 tutorials
  • Machine Learning38 tutorials
  • Deep Learning31 tutorials
  • Generative AI24 tutorials
  • Large Language Models27 tutorials
  • Computer Vision19 tutorials
  • Building Your First AI AgentAI Agents · Intermediate · Mid
  • Neural Networks from First PrinciplesDeep Learning · Beginner · In depth
  • How Large Language Models WorkLarge Language Models · General · Short
  • Prompt Engineering PatternsPrompt Engineering · Intermediate · Mid

Find a tutorial

Tell the assistant what you want to learn. It suggests published chapters.

For example: “I want to learn Rust ownership from the start.” The conversation is kept only in this tab.

0 / 2,000 characters

Enter to send, Shift+Enter for a new line. Do not include personal information.

AI TutorialsKnowledge system 01

Understand AI from First principles.

Structured tutorials. Designed around your depth, experience and curiosity.

Explore topics
Tutorials
245
Domains
10
Levels
04
Depths
03
02Discover

Explore the knowledge system.

Ten domains, indexed like a library. Open any entry to see how deep it goes and where it leads.
  1. Artificial IntelligenceFoundations / 42 tutorials, 42 tutorials. Core ideas behind intelligent systems, from search to reasoning.
  2. Machine LearningModels / 38 tutorials, 38 tutorials. Models that learn from data: training, evaluation, and tuning.
  3. Deep LearningArchitectures / 31 tutorials, 31 tutorials. Neural networks, backpropagation, and modern architectures.
  4. Generative AIGeneration / 24 tutorials, 24 tutorials. Learn modern generative AI concepts and systems.
  5. Large Language ModelsLanguage models / 27 tutorials, 27 tutorials. How LLMs are trained, prompted, evaluated, and deployed.
  6. Computer VisionPerception / 19 tutorials, 19 tutorials. Teach machines to see: classification, detection, segmentation.
  7. Natural Language ProcessingLanguage / 22 tutorials, 22 tutorials. Text understanding, from tokenisation to embeddings.
  8. AI AgentsAutonomy / 16 tutorials, 16 tutorials. Systems that plan, call tools, and complete multi-step tasks.
  9. Prompt EngineeringInterfaces / 14 tutorials, 14 tutorials. Patterns for clear, reliable, and testable prompts.
  10. MLOpsProduction / 12 tutorials, 12 tutorials. Ship, monitor, and maintain models in production.
03Map

Every idea is connected.

The knowledge map shows how topics build on each other. Select a node to trace what it depends on and what it unlocks.
  1. T0 · Origin

  2. T1 · Domains

  3. T2 · Methods

    • Models that create text, images, and code, and how to steer them.

      24 tutorials · 8 beg · 10 int · 6 adv

      Linked → Machine Learning / Deep Learning / Large Language Models / Prompt Engineering

      Explore Generative AI
  4. T3 · Practice

  5. T4 · Systems

04Read

The reading room.

One tutorial, set as a cover story. Below it, every published tutorial in a single dense index.

Featured / 01AI Agents

Featured tutorial: Building AI agents

How intelligent systems reason, plan and use tools.

Learn how AI agents reason, use tools, and complete multi-step tasks.

Level
Intermediate
Length
Mid
Chapters
06
Reading
40 min read
Read tutorial: Building Your First AI Agent
01Agents · Tools · Memory · Reasoning

Contents

  1. Chapter 1: What makes a system an agent
  2. Chapter 2: The reasoning loop
  3. Chapter 3: Designing tools the model can call
  4. Chapter 4: Memory and state between steps
  5. Chapter 5: Handling failures and retries
  6. Chapter 6: Evaluating agent behaviour
05Depth

Choose your depth.

Every topic is written at three lengths and four levels. Pick a point on the matrix and preview what you'll read.
Level
Depth

ReadoutMid × Beginner

Mid, Beginner: about 52 minutes of reading, 1 published tutorial.

52min

Estimated reading time

Chapters
6 (4–7)
Words
5,000–12,000
Difficulty
2 of 4
Published
1 at this depth
Expected detail
Every term defined the first time it appears.
Sample · How a neural network learns

A neural network is made of layers of neurons. Each neuron multiplies its inputs by weights (numbers it can adjust), adds them up, and passes the result on. A loss function scores how far the prediction is from the right answer, and training adjusts the weights to make that score smaller.

Find tutorials at this depth
06Path

Your AI journey.

A suggested route through the system, from first principles to agents. Each stage lists what to know first and where to go next.

Route / 05 stages≈ 61 tutorials · 60 h

Stage 01 / 05

Foundations

What intelligence means for a machine: search, reasoning, and the vocabulary of the field.

Tutorials
≈ 12
Time
6 h
Difficulty
1 of 4
Levels
General → Beginner

Prerequisites

  • None — start here

Topics in this stage

Recommended nextMachine Learning

Start Foundations
07Today
01 / Today's concept

One thing to understand today

Attention

“How transformers decide what information matters.”
Read for 6 min

From · Transformer Internals

Fig. 07 — Self-attention, one sentence
  1. The
  2. animal
  3. didn't
  4. the
  5. because
  6. was

“it” looks hardest at “animal”: that is how the model works out what “it” refers to.

Select an underlined word · weights illustrative

08Start

What do you want to learn?

Search every published tutorial by topic, concept, or keyword. Results are grouped into topics and tutorials.

Trending knowledge

  • Advanced search

You can't do that