Start Learning


Learn AI from zero.
Follow a complete course
build with it

Free. Structured. No signup.

137 core topics and 384 English lessons: A structured, free AI course for understanding modern AI, from large language models and prompting to RAG, agents, AI coding, and building with AI.

Start with the first lessonBrowse the complete course
Course progressFree access
  1. Before You Start0 / 3
  2. AI Foundations0 / 42
  3. Large Language Models0 / 19
  4. AI Harness0 / 62
  5. From Demo to Product0 / 37
  6. AI Engineering Patterns0 / 22
0%Core progress
learned0 / 384
Complete course

Follow the full course structure

Start with foundations, then move through language models, prompting, AI products, agents, coding workflows, and practical building topics. Main lessons are best studied in order; bonus chapters can be opened when useful.

01
Core course3 lessons

Before You Start

Find your starting point and understand how to study AI before entering the main course.

Topic 1
  • Where Are We? The Dunning-Kruger Effect
  • How to Learn So Knowledge Actually Sticks
  • Why Do We Spend So Much Time on Fundamentals?
Open this chapter
03
Core course42 lessons

AI Foundations

Build the first mental model for what AI can do, why it fails, and how to talk to it.

Topic 1Topic 2Topic 3Topic 4
  • Skip the Theory for Now — Look at the Amazing Things It Can Do
  • What Exactly Is AI? It's Really Just Playing "Finish the Sentence"
  • It Isn't Searching the Web for Your Answer
  • It Spouts Nonsense with a Straight Face
  • Treat It Like a Brilliant New Colleague Who Knows Nothing About You
  • 37 more
Open this chapter
04
Core course19 lessons

Large Language Models

Connect training data, tokens, GPT-style models, and hallucinations into one foundation.

Topic 1Topic 2Topic 3Topic 4
  • AI's Food: Training Data
  • Training vs. Inference: Two Completely Different Processes
  • Vocabulary & Training
  • Base Model: The Token-by-Token Prediction Machine
  • GPT's Leap
  • 14 more
Open this chapter
05
Core course62 lessons

AI Harness

Learn context engineering, prompting, safety, agents, tool use, and cost-aware model choices.

Topic 1Topic 2Topic 3Topic 4
  • Context Window: AI's Working Memory
  • Context Overflow: Three Handling Strategies
  • Why LLMs Choose Markdown
  • Markdown Syntax and Engineering Rendering
  • Tell It What to Be, and It Becomes That
  • 57 more
Open this chapter
06
Core course37 lessons

From Demo to Product

Follow a real agent product from working demo to usable AI application.

Case Study IntroTopic 2Agent LoopTopic 4
  • A Real Agent Build Log
  • Text-to-Image vs. Image-to-Image: Two Completely Different Things
  • Using AI to Write Prompts for AI
  • Character Consistency: The Hardest Product Problem
  • When the Model Goes Down, Then What?
  • 32 more
Open this chapter
07
Core course22 lessons

AI Engineering Patterns

Study production agent patterns for context, tools, evaluation, long runs, and safety.

Topic 1Topic 2Topic 3Topic 4
  • Workflow vs Agent: Know What You Need First
  • Five Workflow Patterns
  • From Prompt Engineering to Context Engineering
  • Three Strategies for Long-Context Agents
  • ACI: Agent-Computer Interface
  • 17 more
Open this chapter
08
Core course9 lessons

Harness and Self-Improvement

Understand how harnesses can improve workflows and eventually improve themselves.

Topic 1Topic 2Topic 3Topic 4
  • From Scaffolding to an Self-Improving System
  • Three Design Patterns of Harness
  • Context Engineering: From Handcrafted Prompts to Auto-Evolving Systems
  • Workflow Design: From Manual to Automated Search
  • Letting the Harness Improve Itself
  • 4 more
Open this chapter
09
Core course14 lessons

Vibe Coding Methodology

Build a reusable AI collaboration workflow around goals, context, acceptance, safety, and docs.

Topic 1Topic 2Topic 3Topic 4
  • Why You Need to Set Rules for AI
  • Four-Step Flow: Restate, PRD, Confirm, Code
  • PlayGround: The Component Fitting Room
  • Style Convergence: Don't Ship Eight CSS Kits for One Button
  • Three Comment Elements and Code Protection
  • 9 more
Open this chapter
10
Core course12 lessons

Taste Engineering

Train the ability to judge and describe visual quality when working with AI.

Topic 1Topic 2Topic 3Topic 4
  • Execution Is Free. Judgment Just Got Expensive
  • Where the AI Look Comes From
  • Hierarchy: One Hero per Screen
  • Whitespace & Alignment: Most Ugliness Is Spacing
  • Restraint: Budget Your Colors and Type
  • 7 more
Open this chapter
11
Core course10 lessons

Interaction Engineering

Improve AI-built interfaces with states, error prevention, controls, and flows.

Topic 1Topic 2Topic 3Topic 4
  • It Runs. Now What?
  • The Three States: Loading, Empty, Error
  • Error Prevention & Reversibility: So Users Aren't Afraid to Click
  • Flow Restraint: Every Extra Step Drops Another Batch
  • Conventions: Don't Let AI Invent New Interactions
  • 5 more
Open this chapter
12
Core course19 lessons

AI Product Psychology

Design how users perceive speed, trust, errors, value, and long-term AI product use.

Topic 1Topic 2Topic 3Topic 4
  • Engineering metrics pass. Why do users still call it slow?
  • The Psychology of Waiting: It Was Never Really About Those 5 Seconds
  • Labor Illusion: Make AI Show Its Work
  • Peak-End Rule: Users Only Remember the Peak and the End
  • Trust Calibration: The Best Users Are Half-Skeptical
  • 14 more
Open this chapter
13
Core course13 lessons

Token Cost Engineering

Understand token costs and reduce waste through denser context and better architecture.

Topic 1Topic 2Topic 3Topic 4
  • A Business That Bets Against Its Users
  • How Tokens Are Counted: BPE and the Hidden “Token Tax”
  • Price Sheet at a Glance and the Three Tiers
  • GLM's Short-Output Game: the 200-Token Cliff
  • Qwen's Tier Escape: the 32k Red Line
  • 8 more
Open this chapter
14
Core course13 lessons

Data Structures for AI

Use AI examples to understand arrays, caches, search, graphs, queues, and related structures.

Topic 1Topic 2Topic 3Topic 4
  • It's 2026 — Why Still Learn Data Structures?
  • Arrays: Every Message You Chat Lies in One
  • Stacks: The Secret Behind Cmd+Z and Stack Overflow
  • Queues: An Agent's Work Gets Done in Line
  • Hash Tables: Why Lookups Are Unreasonably Fast
  • 8 more
Open this chapter
15
Core course15 lessons

Algorithms for AI

Build practical intuition for complexity, sorting, divide-and-conquer, search, and sampling.

Topic 1Topic 2Topic 3Topic 4
  • Big-O: See at a Glance How Long Code Will Run
  • Why Longer Context Costs More: The O(n²) Bill
  • Binary Search: The Optimal Number-Guessing Game
  • Sorting: Bubble Sort vs Quicksort Race
  • Sorting's Real Face in AI: Rerank
  • 10 more
Open this chapter
16
Core course25 lessons

Grok Build Deep Dive

Read Grok Build as an optional source deep dive into a production coding agent.

Topic 1Topic 2Topic 3Topic 4
  • How 79 Workspace Members Form a Product
  • Why Rust Makes Sense: Separating Facts from Inferences
  • From Real main() to First Sampling Round
  • Session Actor: Thread, State & Cancellation Boundaries
  • Compaction: 85% Threshold and Optional Two-Pass
  • 20 more
Open this chapter
17
Core course29 lessons

DeepSeek Harness Deep Dive

Read DeepSeek Harness as an optional source deep dive into a plugin-first agent runtime.

Topic 1Topic 2Topic 3Topic 4
  • Everything Is a Plugin: Announcement vs Source
  • Profile / Bundle / Patch: How Far Users Can Reshape the Product
  • Model-visible ⟺ logged: An Invariant That Crashes in Your Face
  • followup / steer / inject: Dual-Queue Inbox
  • What Happens After Esc: Cancel, Crash Recovery, and Re-entry
  • 24 more
Open this chapter
19
Core course9 lessons

Open Source and Local Models

Understand weights, licenses, distillation, and running models locally.

Topic 1Topic 2Topic 3
  • What Are Weights? Everything a Model Knows
  • Real vs. Fake Open Source: How to Read a License
  • Open Source Is a Business: What Each Vendor Is After
  • Emergence: Why Abilities Show Up All at Once
  • Why Make Models Smaller: The Motivation Behind Distillation
  • 4 more
Open this chapter
20
Core course9 lessons

Self Tests

Use self tests to check weak spots and decide what to revisit.

Topic 1Topic 2Topic 3Topic 4
  • 7 Chapter Quizzes · 350 Questions
  • LLM Fundamentals · Chapter Self-Assessment
  • AI Harness · Chapter Quiz
  • From Demo to Product · Chapter Quiz
  • AI Engineering Design Patterns · Chapter Quiz
  • 4 more
Open this chapter
21
Core course16 lessons

One-Person Company Basics

Learn the ownership and compliance basics around brands, code, domains, entities, and equity.

Topic 1Topic 2Topic 3Topic 4
  • Six Weapons: The Right Lock for Each Asset
  • Clear Rights Early: Early Is Investment, Late Is Loss
  • One Trademark Isn't Enough: Take Classes 35, 42, and 41 Together
  • After a Refusal: Clear the Blocking Mark
  • Lock Down the Domains: How a ¥100,000 Ask Became ¥5,000
  • 11 more
Open this chapter
22
Core course6 lessons

SEO and GEO

Understand how search engines and answer engines discover and cite AI products.

Topic 1Topic 2Topic 3Topic 4
  • You Built It. Why Isn't Anyone Coming?
  • The SEO Minimum Viable Checklist: Crawlable, Readable, Indexable
  • GEO: Get AI Engines to Cite You
  • Dissecting This Site: Google Indexes 693 Pages, Bing Only 50
  • Solo Priorities: Write Questions People Actually Search
  • 1 more
Open this chapter
Learning goals

Choose how deep you want to go

The same course can serve different learners. Pick a goal to scope the curriculum, then change it anytime without losing saved progress.

How this goal is scoped

Start from zero

This route focuses on the first useful mental models and practical AI use. It keeps the parts that help a beginner ask better questions, judge answers, and build confidence before going deeper.

Start with this goal
Course coverage77 lessons · about 13 hours
01Before You StartFull chapter
03AI FoundationsFull chapter
04Large Language ModelsSkip for now
05AI Harness13 / 62 lessons
06From Demo to ProductSkip for now
07AI Engineering PatternsSkip for now
08Harness and Self-ImprovementSkip for now
09Vibe Coding Methodology3 / 14 lessons
10Taste EngineeringSkip for now
11Interaction EngineeringSkip for now
12AI Product PsychologySkip for now
13Token Cost EngineeringSkip for now
14Data Structures for AI4 / 13 lessons
15Algorithms for AI4 / 15 lessons
16Grok Build Deep DiveSkip for now
17DeepSeek Harness Deep DiveSkip for now
19Open Source and Local ModelsSkip for now
20Self TestsSkip for now
21One-Person Company Basics5 / 16 lessons
22SEO and GEO3 / 6 lessons
Original guides

Answer the beginner questions first.

These LearnAI0 guides sit above the open course layer. Use them when you need the map before the next lesson.

AI Foundations

How to Learn AI From Scratch

Start with mental models, then learn prompting, context, RAG, agents, and AI coding in that order.

6 min readLearning Path

AI Learning Roadmap for Beginners

A beginner AI roadmap should explain what to learn first, what to postpone, and how each topic connects to real use.

7 min readAI Foundations

What Is Generative AI?

Generative AI creates text, images, code, audio, or other outputs from patterns learned during training and context you provide at use time.

5 min read
Browse all guides

Start from the first lesson

The fastest way to understand AI is to build the right mental model first, then keep moving through the course one lesson at a time.

Start with the first lesson