Courses

Full course notes, mid-effort. Click a course below.

Building a Language Model: From Pretraining to Function Calling

Build one decoder-only language model from random initialization, specialize it for formal proofs, and teach it to use proof tools.

The Agent Harness: Building a Coding Agent from Scratch

Build and measure a headless async coding-agent harness from streaming transport to offline evaluation.

Shipping the Agent: Full-Stack Development of Your Own Claude Code

Build and ship a browser-based coding-agent application with FastAPI, WebSockets, SQLite, background work, and operational evidence.

Building an ML Platform on Azure

A small, low-ops ML platform built twice: first as a Docker Compose proof of concept, then ported to Azure Container Apps behind an explicit environment contract.

Computational Linear Algebra

A numerical-first treatment of linear algebra: the singular value decomposition as the organizing principle, built up from first principles with proofs and working code.