Hands-on track · Learning routes

394 lessons — you don't need them all

Building the full course is our job; how much you study is yours, by goal. The five tracks below are scoped for you, from 78 to 394 lessons: tap a card to see which Parts it covers, what it skips, and why skipping is fine. Once you pick a route, the course catalog trims itself to that path. You can switch tracks or return to the full catalog anytime from the top of the TOC — your progress stays.

Step 1 · Find your fit

Just want to use AI

No coding, no AI product work — you just want it to actually save you time. You'll finish knowing when it's reliable, when it's making things up, and how to ask so you get something useful.

78 lessonsabout 13 hoursBeginner
Start here

Use AI professionally

Still no products and no coding — but you want AI as real productivity. On top of “just use it,” you add how LLMs work and a full Vibe Coding playbook: why it invents, how to set rules, so it stays steady when it works for you.

110 lessonsabout 18 hoursNo coding
Start here

Build AI products

PMs, designers, ops — you need to align with engineers on proposals, judge feasibility, and cost it out. After this, you can defend trade-offs in design review instead of getting waved off with “technically impossible.”

273 lessonsabout 45 hoursNo hands-on coding
Start here

Build it yourself

Engineers or heavy users who want to write an Agent, ship it, and run it. Every core lesson, no skips; follow all six milestones on the hands-on track. Leave the three hardcore source-code electives for when you have bandwidth.

331 lessonsabout 55 hoursRequires coding
Start here

Want it all

No trade-offs — take the three hardcore electives too: Grok Build's Rust source, DeepSeek Harness's TypeScript plugin core, and open-source models' distillation plus local deploy. Finish those three and you can take apart any Coding Agent on the market.

394 lessonsabout 66 hoursIncl. hardcore electives
Start here
Step 2 · See what this path covers

Solid highlight means the whole Part is in; dashed means only some lessons from that Part (count shown after); faded means this route explicitly recommends skipping. Those sections are fine — your goal just doesn't need them.

Why it's cut this way

“Just want to use AI” skips all theory and engineering, and only teaches using AI well: what it's doing, why it invents, how to ask so you get answers, what you can safely hand off. Beyond the beginner FAQ Part, three Harness-core themes stay in — context engineering, Prompt engineering, practical tips; from the collaboration-methods Part, three lessons on setting rules with AI and keeping long chats on track — useful every day even if you never write code.

Picked one? Go

Unsure which track? Fine — all five start from the same lesson. Study two more and you'll feel how deep you want to go. Switching is free, progress stays, and you can change anytime from the top of the TOC.

Read the next lesson first