230+ hands-on lessons across 20 phases. From linear algebra to autonomous agent swarms. Python, TypeScript, Rust, Julia. Every lesson produces something reusable.
Math, ML, deep learning, NLP, vision, speech, transformers, LLMs, agents, swarms. Everything in one place.
Python, TypeScript, Rust, Julia. Build in whatever language fits the problem, not just one.
Every lesson produces reusable prompts, skills, agents, or MCP servers. A portfolio, not a certificate.
Implement from first principles, then learn the framework. Understand why, not just how.
20 phases. Each builds on the last. Click any phase to explore its lessons.
Track overall course completion.
One-line core idea that frames the lesson.
Why this matters. What problem does it solve.
Visual diagrams and intuition-first explanations.
Implement from scratch. No frameworks yet.
Same thing with real frameworks and tools.
The prompt, skill, or agent this lesson produces.
Key AI terms, demystified. What people say vs. what they actually mean.
git clone https://github.com/rohitg00/ai-engineering-from-scratch.git
Prerequisites: You can write code (Python or any language) and you want to understand how AI actually works.