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.

75 min · Reviewed 2026

The Real Test

This capstone is not a toy. You will ship a full-stack AI-assisted project from empty folder to live URL, with tests, CI, deploy, and a short technical write-up. The rubric rewards depth, judgment, and process — not just a working demo.

Project options (pick one)

Habit tracker with analytics: auth, CRUD, charts, streaks, export
AI-powered study buddy: upload notes, generate quizzes, track mastery
Team standup bot: Slack integration, summarizes yesterday/today/blockers, stores history
Expense dashboard: receipt upload, OCR, categorization, monthly report
Open-source contribution: pick a real OSS project, ship one meaningful PR

Non-negotiable requirements

Full stack: frontend + backend + database
Authentication (not demo-grade — real sessions or JWTs)
Automated tests with coverage >= 60% on business logic
CI/CD: every push runs tests; main branch deploys automatically
Deployed to a public URL (Vercel, Fly.io, Railway, Render — anywhere real)
README with: problem statement, architecture diagram, setup steps, deploy steps
Git history with at least 15 commits and descriptive messages
A 5-minute video walkthrough (screen recording + narration)

The agentic workflow to follow

Day 1 — Plan
  Use Claude Code or Codex CLI to create a CLAUDE.md / AGENTS.md with:
    - Stack choices and reasons
    - Schema and API sketch
    - First 10 tasks in priority order
  Open a GitHub repo, push the plan as your first commit.

Day 2-3 — Scaffold
  Agent scaffolds the backend (routes, DB, auth).
  You review every file before committing.
  Write tests for each route as you go.

Day 4-5 — Frontend
  Prototype UI with v0 or Lovable, export to repo.
  Or build in Cursor using shadcn/ui components.
  Wire frontend to backend, end-to-end.

Day 6 — CI/CD
  Set up GitHub Actions with test + lint + build.
  Connect deploy previews (Vercel is easiest).
  Add an AI release-notes action to every PR.

Day 7 — Polish and Record
  Fix edge cases, improve error messages.
  Write the README.
  Record the video walkthrough.Seven focused days. Not seven intense days — regular days, with a plan.

The three reviews that matter

Review	By	When
Security red-team	A fresh AI session with red-team prompt	Before deploy
Code quality	Claude Code or Copilot review	On every PR
UX + accessibility	Human testers, at least 2	Before the video

The write-up that gets you hired

Your README or accompanying blog post should answer: what did the agent do well? Where did it fail and how did you recover? What did you design that it could not have generated? Interviewers love this because it signals self-awareness, and self-awareness is the rarest signal.

Grading rubric

Working deployment: pass/fail
Test coverage and CI green: pass/fail
Code quality: readable, typed, no obvious security holes
Judgment: can you articulate tradeoffs in the video?
Process: git history shows thoughtful iteration, not one giant commit
Documentation: someone could set up your project in 10 minutes

After the capstone

Post the repo publicly with a strong README
Share the demo link on LinkedIn with a before/after of what you learned
Tag 3 engineers you admire and ask for honest feedback
Pick your next project — the skill compounds only if you keep shipping
Consider contributing back to an open-source tool you used in the build

The future belongs to engineers who ship. AI just made shipping more accessible than ever.
— A Tendril alum

The big idea: you now have a complete AI-assisted engineering workflow — from planning with an agent through testing, deploying, and documenting. That's the baseline of an AI-literate engineer in 2026. Go build something that matters.

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-coding-capstone-full-stack-creators

What is the core idea behind "Capstone: Ship a Real Full-Stack AI-Assisted Project"?
1. The creators capstone. You scope, design, build, test, deploy, and document a real full-stack project using an agentic workflow — end to end.
2. data storage
3. 'How do I keep my database safe from common mistakes?'
4. Configure AI review to catch real issues — not nits — by tuning what it comments…
Which term best describes a foundational idea in "Capstone: Ship a Real Full-Stack AI-Assisted Project"?
1. full-stack
2. capstone
3. agentic workflow
4. CI/CD
A learner studying Capstone: Ship a Real Full-Stack AI-Assisted Project would need to understand which concept?
1. capstone
2. agentic workflow
3. full-stack
4. CI/CD
Which of these is directly relevant to Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. capstone
2. full-stack
3. CI/CD
4. agentic workflow
Which of the following is a key point about Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. Habit tracker with analytics: auth, CRUD, charts, streaks, export
2. AI-powered study buddy: upload notes, generate quizzes, track mastery
3. Team standup bot: Slack integration, summarizes yesterday/today/blockers, stores history
4. Expense dashboard: receipt upload, OCR, categorization, monthly report
Which of these does NOT belong in a discussion of Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. Team standup bot: Slack integration, summarizes yesterday/today/blockers, stores history
2. Habit tracker with analytics: auth, CRUD, charts, streaks, export
3. data storage
4. AI-powered study buddy: upload notes, generate quizzes, track mastery
Which statement is accurate regarding Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. Authentication (not demo-grade — real sessions or JWTs)
2. Automated tests with coverage >= 60% on business logic
3. Full stack: frontend + backend + database
4. CI/CD: every push runs tests; main branch deploys automatically
Which of these does NOT belong in a discussion of Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. Full stack: frontend + backend + database
2. Automated tests with coverage >= 60% on business logic
3. data storage
4. Authentication (not demo-grade — real sessions or JWTs)
What is the key insight about "Budget alert" in the context of Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. A full-stack project can burn real API dollars. Cap your API usage daily, use cheap models for routine tasks, and keep p…
2. data storage
3. 'How do I keep my database safe from common mistakes?'
4. Configure AI review to catch real issues — not nits — by tuning what it comments…
Which statement accurately describes an aspect of Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. data storage
2. This capstone is not a toy. You will ship a full-stack AI-assisted project from empty folder to live URL, with tests, CI, deploy, and a shor…
3. 'How do I keep my database safe from common mistakes?'
4. Configure AI review to catch real issues — not nits — by tuning what it comments…
What does working with Capstone: Ship a Real Full-Stack AI-Assisted Project typically involve?
1. data storage
2. 'How do I keep my database safe from common mistakes?'
3. Your README or accompanying blog post should answer: what did the agent do well? Where did it fail and how did you recover? What did you des…
4. Configure AI review to catch real issues — not nits — by tuning what it comments…
Which of the following is true about Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. data storage
2. 'How do I keep my database safe from common mistakes?'
3. Configure AI review to catch real issues — not nits — by tuning what it comments…
4. The big idea: you now have a complete AI-assisted engineering workflow — from planning with an agent through testing, deploying, and documen…
Which best describes the scope of "Capstone: Ship a Real Full-Stack AI-Assisted Project"?
1. It focuses on The creators capstone. You scope, design, build, test, deploy, and document a real full-stack projec
2. It is unrelated to ai-coding workflows
3. It applies only to the opposite beginner tier
4. It was deprecated in 2024 and no longer relevant
Which section heading best belongs in a lesson about Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. data storage
2. Project options (pick one)
3. 'How do I keep my database safe from common mistakes?'
4. Configure AI review to catch real issues — not nits — by tuning what it comments…
Which section heading best belongs in a lesson about Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. data storage
2. 'How do I keep my database safe from common mistakes?'
3. Non-negotiable requirements
4. Configure AI review to catch real issues — not nits — by tuning what it comments…

← Back to interactive lesson

Tendril · Creators · AI-Assisted Coding

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.

75 min · Reviewed 2026

The Real Test

Project options (pick one)

Habit tracker with analytics: auth, CRUD, charts, streaks, export
AI-powered study buddy: upload notes, generate quizzes, track mastery
Team standup bot: Slack integration, summarizes yesterday/today/blockers, stores history
Expense dashboard: receipt upload, OCR, categorization, monthly report
Open-source contribution: pick a real OSS project, ship one meaningful PR

Non-negotiable requirements

Full stack: frontend + backend + database
Authentication (not demo-grade — real sessions or JWTs)
Automated tests with coverage >= 60% on business logic
CI/CD: every push runs tests; main branch deploys automatically
Deployed to a public URL (Vercel, Fly.io, Railway, Render — anywhere real)
README with: problem statement, architecture diagram, setup steps, deploy steps
Git history with at least 15 commits and descriptive messages
A 5-minute video walkthrough (screen recording + narration)

The agentic workflow to follow

Day 1 — Plan
  Use Claude Code or Codex CLI to create a CLAUDE.md / AGENTS.md with:
    - Stack choices and reasons
    - Schema and API sketch
    - First 10 tasks in priority order
  Open a GitHub repo, push the plan as your first commit.

Day 2-3 — Scaffold
  Agent scaffolds the backend (routes, DB, auth).
  You review every file before committing.
  Write tests for each route as you go.

Day 4-5 — Frontend
  Prototype UI with v0 or Lovable, export to repo.
  Or build in Cursor using shadcn/ui components.
  Wire frontend to backend, end-to-end.

Day 6 — CI/CD
  Set up GitHub Actions with test + lint + build.
  Connect deploy previews (Vercel is easiest).
  Add an AI release-notes action to every PR.

Day 7 — Polish and Record
  Fix edge cases, improve error messages.
  Write the README.
  Record the video walkthrough.Seven focused days. Not seven intense days — regular days, with a plan.

The three reviews that matter

Review	By	When
Security red-team	A fresh AI session with red-team prompt	Before deploy
Code quality	Claude Code or Copilot review	On every PR
UX + accessibility	Human testers, at least 2	Before the video

The write-up that gets you hired

Grading rubric

Working deployment: pass/fail
Test coverage and CI green: pass/fail
Code quality: readable, typed, no obvious security holes
Judgment: can you articulate tradeoffs in the video?
Process: git history shows thoughtful iteration, not one giant commit
Documentation: someone could set up your project in 10 minutes

After the capstone

Post the repo publicly with a strong README
Share the demo link on LinkedIn with a before/after of what you learned
Tag 3 engineers you admire and ask for honest feedback
Pick your next project — the skill compounds only if you keep shipping
Consider contributing back to an open-source tool you used in the build

The future belongs to engineers who ship. AI just made shipping more accessible than ever.
— A Tendril alum

End-of-lesson check

15 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-coding-capstone-full-stack-creators

What is the core idea behind "Capstone: Ship a Real Full-Stack AI-Assisted Project"?
1. The creators capstone. You scope, design, build, test, deploy, and document a real full-stack project using an agentic workflow — end to end.
2. data storage
3. 'How do I keep my database safe from common mistakes?'
4. Configure AI review to catch real issues — not nits — by tuning what it comments…
Which term best describes a foundational idea in "Capstone: Ship a Real Full-Stack AI-Assisted Project"?
1. full-stack
2. capstone
3. agentic workflow
4. CI/CD
A learner studying Capstone: Ship a Real Full-Stack AI-Assisted Project would need to understand which concept?
1. capstone
2. agentic workflow
3. full-stack
4. CI/CD
Which of these is directly relevant to Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. capstone
2. full-stack
3. CI/CD
4. agentic workflow
Which of the following is a key point about Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. Habit tracker with analytics: auth, CRUD, charts, streaks, export
2. AI-powered study buddy: upload notes, generate quizzes, track mastery
3. Team standup bot: Slack integration, summarizes yesterday/today/blockers, stores history
4. Expense dashboard: receipt upload, OCR, categorization, monthly report
Which of these does NOT belong in a discussion of Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. Team standup bot: Slack integration, summarizes yesterday/today/blockers, stores history
2. Habit tracker with analytics: auth, CRUD, charts, streaks, export
3. data storage
4. AI-powered study buddy: upload notes, generate quizzes, track mastery
Which statement is accurate regarding Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. Authentication (not demo-grade — real sessions or JWTs)
2. Automated tests with coverage >= 60% on business logic
3. Full stack: frontend + backend + database
4. CI/CD: every push runs tests; main branch deploys automatically
Which of these does NOT belong in a discussion of Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. Full stack: frontend + backend + database
2. Automated tests with coverage >= 60% on business logic
3. data storage
4. Authentication (not demo-grade — real sessions or JWTs)
What is the key insight about "Budget alert" in the context of Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. A full-stack project can burn real API dollars. Cap your API usage daily, use cheap models for routine tasks, and keep p…
2. data storage
3. 'How do I keep my database safe from common mistakes?'
4. Configure AI review to catch real issues — not nits — by tuning what it comments…
Which statement accurately describes an aspect of Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. data storage
2. This capstone is not a toy. You will ship a full-stack AI-assisted project from empty folder to live URL, with tests, CI, deploy, and a shor…
3. 'How do I keep my database safe from common mistakes?'
4. Configure AI review to catch real issues — not nits — by tuning what it comments…
What does working with Capstone: Ship a Real Full-Stack AI-Assisted Project typically involve?
1. data storage
2. 'How do I keep my database safe from common mistakes?'
3. Your README or accompanying blog post should answer: what did the agent do well? Where did it fail and how did you recover? What did you des…
4. Configure AI review to catch real issues — not nits — by tuning what it comments…
Which of the following is true about Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. data storage
2. 'How do I keep my database safe from common mistakes?'
3. Configure AI review to catch real issues — not nits — by tuning what it comments…
4. The big idea: you now have a complete AI-assisted engineering workflow — from planning with an agent through testing, deploying, and documen…
Which best describes the scope of "Capstone: Ship a Real Full-Stack AI-Assisted Project"?
1. It focuses on The creators capstone. You scope, design, build, test, deploy, and document a real full-stack projec
2. It is unrelated to ai-coding workflows
3. It applies only to the opposite beginner tier
4. It was deprecated in 2024 and no longer relevant
Which section heading best belongs in a lesson about Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. data storage
2. Project options (pick one)
3. 'How do I keep my database safe from common mistakes?'
4. Configure AI review to catch real issues — not nits — by tuning what it comments…
Which section heading best belongs in a lesson about Capstone: Ship a Real Full-Stack AI-Assisted Project?
1. data storage
2. 'How do I keep my database safe from common mistakes?'
3. Non-negotiable requirements
4. Configure AI review to catch real issues — not nits — by tuning what it comments…

← Back to interactive lesson