Lesson 38 of 1455
Your First Capstone — Ship a Small Project
Bring it all together. Pick one of three starter projects, plan it, build it with AI, and deploy it. You are now a builder who ships.
Builders · AI-Assisted Coding · ~27 min read
You Have the Tools. Now Use Them.
This is the builders capstone. You will scope a small project, build it with AI help, commit to git, and deploy it to a real URL. The rubric is not cleverness. It is shipping something that works and that you can explain.
Pick one of these three
- Flashcard app: a static site that loads cards from a JSON file and quizzes you
- Personal homepage: about you, projects, contact, styled deliberately
- Weather dashboard: enter a city, see today's forecast using a free API
The capstone contract
- 1Write a one-paragraph README of what the project does and why you chose it
- 2Break the work into at least four git commits with descriptive messages
- 3Use AI for at least half the code, but read and understand every line
- 4Deploy to a public URL (GitHub Pages, Vercel, or Netlify — all free)
- 5Record a 60-second video of you using your project
A scoping worksheet that actually works
Fill this in BEFORE you start typing. Half the projects that fail, fail because nobody wrote this down.
Project name: ______________________ One-line description: ______________________ Minimum viable version (what works on day 1): - ______________________ - ______________________ - ______________________ Stretch goals (only if above is done): - ______________________ - ______________________ Files I expect to create: - index.html / app.py / etc. - ______________________ - ______________________ My first prompt to the AI will be: "______________________"A typical day of the build
- 1Open your worksheet, pick one task list
- 2Write a prompt that names inputs and expected outputs
- 3Review the AI draft, run it, commit when it works
- 4Move to the next task list — resist sidequests
Deployment options at a glance
Compare the options
| Host | Best for | Setup |
|---|---|---|
| GitHub Pages | Static HTML/CSS/JS | Push to repo, enable Pages |
| Vercel | Next.js and full-stack | Connect repo, click Deploy |
| Netlify | Drag-and-drop static sites | Drop your folder on their dashboard |
| Replit | Python, Node, everything | Write in browser, click Run |
Your 60-second video
Record your screen while you use your project. Narrate what the project does, show it working, and mention one thing you learned. Upload to YouTube as unlisted. Put the link in your README. This is now a portfolio piece.
“Ship it. Then ship it again. Then ship it once more.”
Key terms in this lesson
The big idea: building something small and shipping it is a bigger lesson than reading a hundred tutorials. You now have a URL you can point to and say, I made that.
End-of-lesson quiz
Check what stuck
8 questions · Score saves to your progress.
Lesson help
Questions are best handled with a grown-up here.
For this age range, Tendril keeps freeform AI chat paused until parent/guardian consent and child-safe moderation are fully verified. Use the quiz, notes, and related lessons below, or ask a parent, guardian, teacher, or librarian to work through the question with you.
Progress saved locally in this browser. Sign in to sync across devices.
Related lessons
Keep going
Creators · 75 min
Capstone: Ship a Real Full-Stack AI-Assisted Project
The creators capstone. You scope, design, build, test, deploy, and document a real full-stack project using an agentic workflow — end to end.
Creators · 50 min
AI-Assisted Code Review Workflows (for Teams)
Code review is the highest-leverage touchpoint in a team. Automating the noise with AI frees humans to focus on the irreducibly human parts. Let's design the workflow.
Creators · 50 min
Deploy Pipelines With AI in the Loop
AI belongs in CI/CD too. From PR previews to rollback judgment calls, agents can operate inside your pipeline safely — if you scope them right.
