Orientation: start here
Start here before tools or builds. Work through these steps in order. They give you the mental model the whole bootcamp rests on.
- 1
Know what building with AI means (and is not)
You are not going to hand-write software. You describe what you want clearly and direct AI tools to build it. The job is directing and judging what came back, not typing code. Vague brief → plausible wrong output. Specific brief → the right thing.
- 2
Learn the four layers every app shares
Frontend (what users see), backend (rules and logic), data (memory that survives refresh), and auth (who is allowed in). When someone opens your URL, signs up, does something, and comes back tomorrow, all four layers worked. That is your Week 1 goal.
- 3
See how the capstone spine works
You pick one product and build it across four weeks: live URL in Week 1, AI features in Week 2, workflows and agents in Week 3, evals and polish in Week 4, then Demo Day. Not four throwaway homework apps.
- 4
Know what Week 1 ships
A live web app at a real URL: sign-up, login, your core action, data that survives a refresh, and at least one AI feature that actually runs in the published app.
- 5
Set up before Session 1
After this reading: Lovable account, Maven + WhatsApp, capstone one-liner, then optional check-in. The Session 1 checklist at the end of pre-course shows mandatory vs good-to-have.
The four layers (detail)
Frontend
What the user sees and touches - screens, buttons, forms, colours. Its job is to show things and collect what the user types or taps. It decides nothing on its own.
Backend
The brain. When a user clicks a button, the frontend hands the request to the backend, which runs the rules and calculations. The user never sees it, but nothing meaningful happens without it.
Data
The memory - users, inputs, history. When you log in a week later and your stuff is still there, that is the data layer. When an app "forgets" on refresh, that is almost always a data problem.
Auth
The gatekeeper - who is this person, and what are they allowed to see? Sign-up, login, and permissions all live here. Auth is what separates a real product from a demo.
A user types their email and password and clicks Log in. The frontend collects those and hands them over. The backend checks them against the data. Auth confirms identity and permissions. The backend sends the answer back; the frontend shows the logged-in screen. Four layers, one click.
Tip
The skill you are actually learning
When a build misbehaves, name the layer that is failing (frontend, backend, data, or auth?). That tells you what to ask Lovable to fix. Treat the AI like a brilliant, fast junior who takes everything literally.
Critical
Before Session 1: Lovable first
Your highest-leverage setup job is a Lovable account you can log into. Do that in the next lesson. Capstone seed and check-in come after.
Done when
- You can name the four layers and what each one does
- You understand that your job is to direct and judge, not to hand-write code
- You know to set up Lovable next