406 chapters · 3 courses · the first chapters are free

Learn to build with AI.Hands on, from day one.

Real courses on AI agents, machine learning and robotics, with code you can run, quizzes that make it stick, and a tutor beside you.

Start learning See what you will learn

One-click sign-in with Google. We only receive your name and email.

Build an agent · Chapter 12 · The agent loop

agent.py

while not done:
  step = model.plan(goal, memory)
  result = tools.run(step)
  memory.add(result)
  done = result.solved

Ran in 0.8 s

step 1 search("flights to Oslo") step 2 compare(3 results) solved in 2 steps

Check yourself

What makes this an agent and not a single prompt?

It uses a bigger model
It loops: act, observe, decide
It writes longer answers

Nano

Want a harder one? I can quiz you on tool errors next.

6-day streak

48 of 77

406: chapters, each 3 to 10 minutes
1,572: code examples to read and run
500: quiz questions inside the chapters
320 h: of material to learn from

Why Nanofuze

Everything you need to go from curious to shipping.

Not a video playlist and not a wall of links: one place that teaches, tests you and answers your questions.

Code that actually runs
Every example marked as runnable was executed, and the output printed under it is the output you get. No hand-waving, no code that only looks right.
Quizzes that make it stick
Questions inside the chapters feed a spaced-review queue that brings an idea back just before you would forget it.
A tutor on every page
Nano knows the chapter you are on. Ask it to explain simply, quiz you or set an exercise, by typing or by voice.
Paths to a goal
6 week-by-week programs of 50 hours or more, each with a hands-on lab every week: robotics, AI from zero, agents, machine learning, modern AI models and building projects.
Your learning profile
Levels, a streak, a calendar of the days you studied, achievements, saved chapters and notes, all kept in your own browser and yours to export.
Free to try
The front page and the first three chapters of every course are open to everyone. Sign in with Google when you want the rest.

The courses

Three full courses. One goal: you can build it.

Each course is a complete syllabus from the first idea to a working project, with checks along the way.

92 chapters · 55.1 hours
Build an agent
Learn AI from the basics and build agents: tools, MCP, retrieval, hooks and teams.
- Explain how a language model, a context window and retrieval fit together
- Write an agent loop from scratch and know exactly what every message in it means
- Design tools a model can use reliably, with structured output and clear errors
481 code samples72 quizzes13 parts
View the syllabus
159 chapters · 145.7 hours
Machine Learning & Deep Learning
From a line through points to large language models: the maths, classical models, neural networks, vision, language, generative AI and production, built from scratch.
- Explain how a model learns from examples and reduce that to a loss and an update rule
- Use vectors, matrices, derivatives and probability with confidence, and run each idea in numpy
- Prepare data, split it honestly and avoid leakage and bias
505 code samples308 quizzes18 parts
View the syllabus
155 chapters · 118.8 hours
Robotics & Physical AI
From kinematics to humanoids: control, perception, learning, vision-language-action models, ROS 2, safety and projects.
- Explain the sense, think, act loop and how every robot is organised
- Describe a robot's pose with frames and transforms, and compute where its hand is (kinematics)
- Choose motors, gearboxes, sensors and computers for a real design
586 code samples120 quizzes16 parts
View the syllabus

Learning paths

Know where you are going? Take the short route.

A path is a week-by-week program to one goal, 50 hours or more, with a hands-on lab every week. Pick the one that matches what you want to build or understand.

Featured pathCurious about robots and embodied AI

Robotics and physical AI.

A 24-week program: 13 weeks from coordinate frames to learned robot policies, with 13 labs on any laptop, then an 11-week build of NanoRover, a real robot with vision, hearing, many sensors and a safe AI brain, from parts list to wiring to code.

24 weeks123 h123 chaptersAll levels

See the 24-week program

What you will build

A physics simulator for a robot arm
A Kalman filter and a particle filter
A path planner and a model-predictive controller
A pick and place with a measured success rate
A safety supervisor with fault injection

Start hereNo background needed
AI from zero
A 13-week program for a complete beginner: Python and data, your first models, how neural networks and language models work, and your first AI agent, with a hands-on lab every week.
13 weeks64 h75 chaptersBeginner
Developers
Build AI agents
A 14-week program from the agent loop to a launched agent: tools, memory and retrieval (RAG), MCP, the Claude and OpenAI SDKs, many agents, evals, safety and shipping to production, with hands-on labs every week and a capstone project.
14 weeks60 h92 chaptersIntermediate
Aspiring ML engineers and analysts
Machine learning engineer
A 14-week program: the maths in a few pages, honest data work, classical models and neural networks you build from scratch, then PyTorch, MLOps and serving, with a lab every week and an end-to-end capstone.
14 weeks67 h91 chaptersAll levels
You use them; now see inside
Modern AI models
A 14-week program on how today's models work: convolutions, tokenisers and attention, a small GPT you train, adapters, quantisation and evaluation, then autoencoders, diffusion and reinforcement learning, with a lab every week.
14 weeks70 h69 chaptersAdvanced
Hands-on, code first
Learn by building
A ladder of twelve projects that grow in ambition, each with the lab behind it: a spam filter, house prices, a digit recogniser, an image classifier, a recommender, a language model, three agents, a simulated robot arm and an ML capstone.
12 weeks72 h24 chaptersAll levels

All 6 paths and the courses

How you learn

Read it. Run it. Check it. Ask about it.

01
Read
Short chapters written to be understood on the first read: the idea, a picture, an example and what to remember.
02
Run
Run the examples and see real output. Change a line, run it again, and watch what happens.
03
Check
Answer the questions inside the chapter. What you miss comes back for review, spaced out so it sticks.
04
Ask
Stuck? Nano explains it another way, quizzes you or sets an exercise, without leaving the page.

Who it is for

Made for people who build.

If you learn best by doing, this is for you.

Developers moving into AI
You can code. Learn how agents, tools, retrieval and evaluation fit together, and ship something that works.
The agents path
Students and career switchers
Start from zero with plain language and pictures, and build up to real models without skipping the maths that matters.
Start from zero
Technical leaders and product people
Know what is possible, what it costs and what to ask your team, with sources you can check.
AI in production
Makers and robotics fans
Go from sensors and control to learning-based robots, with build projects at the end of each part.
The robotics path

Built to be trusted

The boring parts are done properly.

A learning site is only worth your time if you can believe it.

Code you can trust
Examples marked as runnable were executed, and the output shown is the output we got. Nothing is copied or rewritten from other sites.
No tracking unless you say yes
Analytics stays off until you accept it, and what you type, such as searches and messages, is never shared.
Honest about limits
Each course says what was run and what was only checked, and flags facts that come from a public source we could not verify against the original.
Your data stays small
We receive your name and email from Google, nothing else. Your progress and notes stay in your own browser.

Our standards About Nanofuze

Your first chapter is ten minutes away.

Start learning Browse the catalog

Learn to build with AI.Hands on, from day one.

Everything you need to go from curious to shipping.

Code that actually runs

Quizzes that make it stick

A tutor on every page

Paths to a goal

Your learning profile

Free to try

Three full courses. One goal: you can build it.

Know where you are going? Take the short route.

Read it. Run it. Check it. Ask about it.

Read

Run

Check

Ask

Made for people who build.

The boring parts are done properly.

Code you can trust

No tracking unless you say yes

Honest about limits

Your data stays small

Your first chapter is ten minutes away.

Learn to build with AI.Hands on, from day one.

Everything you need to go from curious to shipping.

Code that actually runs

Quizzes that make it stick

A tutor on every page

Paths to a goal

Your learning profile

Free to try

Three full courses. One goal: you can build it.

Know where you are going? Take the short route.

Read it. Run it. Check it. Ask about it.

Read

Run

Check

Ask

Made for people who build.

The boring parts are done properly.

Code you can trust

No tracking unless you say yes

Honest about limits

Your data stays small

Your first chapter is ten minutes away.