Choose your theme color.
TheFocus.AI Student
Build a fully functional AI coding assistant from scratch — without writing a single line of code. Learn how agents actually work by building one.
A hands-on tutorial teaching patterns for working with AI coding assistants — research, delegation, parallelism, and semantic enrichment. The email pipeline is the example; the patterns are the point.
A five-module ladder from your first LoRA to an agent that trains on its own verified successes. Apple Silicon primary, Jetson Thor for scale.
A practical guide to thinking about AI — from your first hands-on exercise to compound production systems.
Get hands-on with local AI — install Ollama, run models offline, and learn prompting techniques.
Instead of answering questions on this website, copy the calibration prompt below and paste it into Claude, ChatGPT, or your local tutoring assistant. The assistant will ask you questions to learn about your goals, coding experience, and background, then save your profile observations directly back to the site.
If your assistant is running in a sandbox or restricted network proxy and hits a 403 / allowlist wall, paste the JSON output it assembled below to save your profile details:
Use a student ID from another device or a tutoring session. This browser will adopt that ID and its progress and profile.
Clear all your lesson completions so you can redo them. Your student ID and profile are kept.
Progress has been reset. Go to the homepage
Something went wrong. Try again or disenroll instead.
Remove your student ID, progress, and theme from this browser. Your data on the server is not affected.
You have been disenrolled. Go to the homepage
Every course on this site was developed in collaboration with AI coding agents — the same tools you'll learn to build. We practice what we teach: the content, the design, and the platform itself are products of human direction amplified by machine capability.
No accounts. No tracking. No paywall. The code is open source, the content is free, and the methods are transparent. Because the best way to build trust in AI is to show exactly how it's done.
View on GitHub →