Seed your capstone
What is the capstone?
Your capstone is the one product you will build across all four weeks. It is not four separate homework apps - it is one system that gets better each week: a 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.
Why we do it this way
Most AI courses leave you with disconnected demos. We do not. When every assignment extends the same product, you finish with a portfolio piece you can show on LinkedIn and walk through in an interview - not a folder of throwaway exercises.
Choosing your capstone now also means Week 1 is not a blank screen. You walk into the first session knowing what you are building and for whom, so the live Lovable build starts on your idea, not a generic template.
What makes a good capstone
- Small enough to finish in four weeks - one clear job done well, not five half-built features.
- Real to you - from your work, a side project, or a problem you personally have.
- All four layers - a user signs in, does something, and their work is still there when they return.
Example
Seeds that fit the course
- A client intake tool that takes a form and drafts a proposal.
- An internal dashboard that answers questions about team data.
- A booking flow that sends reminders automatically.
- A tool that turns long documents into short briefs.
- A support assistant grounded in your help docs.
Watch out
Seeds that stall capstones
- Needs a huge dataset or custom-trained model.
- So broad it cannot be demoed in three minutes.
- A vague theme ("something with AI for marketing") instead of one user and one core action.
Your one-page seed (four questions)
- What does it do? One sentence. If it takes more than one, narrow it.
- Who is it for? Name the actual person who would use it.
- What is the single most important action it needs to do? This is what you build first in Week 1.
- What would make you proud to demo on Demo Day? That is your north star for scope.
Include your capstone one-liner in your pre-session check-in post. If you write the full page, link to it (Google Doc, Notion, or gist). Reading other students' seeds in Maven or WhatsApp is one of the fastest ways to see what "well-scoped" looks like.
Done when
- You answered all four seed questions (even if briefly)
- Your capstone one-liner is ready for the pre-session check-in
- You can explain in one sentence who uses your product and what they do with it