Build It, Then Use It: How I wrote 435 AI engineering lessons from scratch

Description and use

A story about creating a 435-lesson AI engineering curriculum following the 'Build It, Then Use It' rule. The course covers 20 phases, from linear algebra to multi-agent systems. Each algorithm is first implemented from scratch using NumPy, then compared with a production library. This helps developers understand the internals of frameworks and become confident in their use.

Problem

There is a gap between using AI tools daily and feeling ready to ship production code. Frameworks like PyTorch and libraries like tiktoken act as black boxes, hiding the underlying mechanics. Most courses either teach math without code or code without math, leaving developers unable to debug or scale their implementations when issues arise.

Outcome

The author successfully created a 435-lesson, MIT-licensed curriculum called 'ai-engineering-from-scratch'. The curriculum covers 20 phases of AI engineering, from linear algebra to multi-agent systems. By following the 'Build It, Then Use It' rule, the author produced a resource that helps developers understand the internals of frameworks and build production-ready skills.

Workflow

• Identify a core AI algorithm (e.g., attention, gradient descent).
• Implement the algorithm from scratch using only NumPy and standard libraries (Build It).
• Run the same input and data through the production framework (e.g., PyTorch, tiktoken).
• Compare the outputs of the custom implementation and the framework to verify numerical precision.
• Iterate through 20 phases, building increasingly complex systems (e.g., small LLM, agent loop, multi-agent system).
• Generate reusable artifacts like prompt templates, skill specs, and MCP servers for each lesson.

Evidence

The first time I wrote a tokenizer, I did it with a for loop. I counted byte pairs by hand, merged the most common ones, and waited about forty seconds for it to chew through a small corpus. The output was slow. The output was ugly. The output was correct.

Source

Then I ran the same input through tiktoken and watched it finish in forty milliseconds. That was the moment tiktoken stopped being magic. It was the same thing I had written the night before, in Rust, with the loop unrolled and the cache warm.

Source

I wrote 435 lessons under that rule. They live in a free, MIT-licensed curriculum called **ai-engineering-from-scratch**.

Source