Series

Structured learning paths and technical deep dives.
Read them in order, like chapters in a book.

4 PartsIn Progress

Building an Agent

A comprehensive series on building AI coding agents from scratch, covering everything from basic tool integration to advanced features like agentic search and subagents.

Building An Agent

Implementing a coding agent in around 200 lines of Javascript code

13 min read

Building a Coding CLI with React Ink

Migrating Our Coding Agent to React Ink

18 min read

Building your own AI SDK

Switch between models with your own custom router

32 min read

Agentic Search

Models can't do much without the right context, agentic search does just that

13 min read

Coming Soon

1 PartsIn Progress

LLMs From Scratch

Working through Stanford's CS336 and documenting what I learn at each step — from tokenization to training.

Implementing BPE

Building a Byte-Pair Encoding tokenizer from scratch

34 min read

Coming Soon

2 PartsIn Progress

Reinforcement Learning From Scratch

A series on building reinforcement learning agents from scratch, covering everything from basic concepts to advanced techniques.

Spinning Up RL

Getting started with reinforcement learning

14 min read

Reversing Chinese Poetry

Creating our first RL Pipeline with Verifiers

22 min read

Coming Soon

3 PartsIn Progress

Structured Outputs From Scratch

Building a structured output parser from first principles — from JSON Schema to regex to FSM to constrained decoding.

Pydantic to Regex: Compiling JSON Schemas for Structured Outputs

Build a recursive JSON Schema-to-regex compiler from first principles

9 min read

Building our FSM

Going beyond a simple regex to an FSM for quick lookups

18 min read

Compiling IR to NFA

Turn regex IR into a graph-based automaton for fast next-step lookup

14 min read