The open-source AI tool that turns raw app ideas into build-ready product specs.
Created by Enterprise DNA -- a leading data and AI education company.
What is it? • Built with AI • Features • Tech Stack • Quick Start • Self-Hosting • Architecture • Dev with AI • Contributing • License
AI App Idea Generator is an open-source web app that takes a rough idea -- a few sentences describing what you want to build -- and uses AI to produce a complete, build-ready product specification. It's the fastest way to go from "I have an idea" to "I have a plan I can actually hand to a developer (or AI coding agent)."
Think of it as an AI product manager in a box: describe the problem, pick your industry and function, and the app generates:
- A clear project title and pitch
- A full questionnaire walkthrough that sharpens the concept
- A detailed outline document
- Functional requirements
- Tech stack recommendations
- Frontend guidelines
- Backend structure
- File structure
- Implementation plan and task breakdown
All generated content is saved to your own Supabase project, so you can revisit, edit, and export later.
Most "startup idea generators" give you a sentence and walk away. AI App Idea Generator is different:
- Full product specs, not hype -- You get a PRD, tech stack, file structure, and tasks. Not just a tagline.
- Questionnaire-driven -- The app asks smart follow-up questions to tighten the scope before generating docs.
- Industry- and function-aware -- Ideas are tailored to your vertical (Healthcare, Finance, Retail, etc.) and business function (Sales, Operations, HR, etc.)
- 17 specialized AI endpoints -- Each document type (outline, tech stack, tasks, etc.) has its own dedicated Supabase Edge Function with a tuned prompt.
- Self-hostable -- Bring your own OpenAI API key, run it on your own Supabase project, own every generated artifact.
- Built to be handed to AI coders -- The output format is designed so you can paste it straight into Claude Code, Cursor, or any other AI coding tool and start building.
This entire application was built using AI-assisted development tools. Enterprise DNA believes in the future of AI-augmented software development, and this project is a reference for what's possible. Every layer -- from the Supabase edge functions to the React UI -- was written collaboratively with AI coding agents.
| Tool | Role |
|---|---|
| Claude Code by Anthropic | Primary development tool. Claude Code acted as the AI coding agent, building features end-to-end across the full stack -- from Supabase edge functions to React components to page layouts. |
| Cursor | AI-powered IDE used throughout development for code navigation, inline edits, and rapid iteration. |
| GitHub Copilot | AI pair programming assistant for code completion and pattern matching. |
Enterprise DNA is committed to demonstrating that AI tools are not just productivity boosters -- they are a new way to build software. This project serves as a reference implementation for AI-assisted full-stack development.
- Free-form app idea textarea on the landing page
- Guided inspiration flow: pick industry + business function + describe your daily tasks, get tailored idea suggestions
- Pre-made templates by industry (Healthcare, Education, Finance, Retail, Manufacturing, Technology, Real Estate, Transportation, Hospitality)
- AI-generated project titles from free-form descriptions
- Dynamic AI-generated questions that adapt to your idea
- Follow-up question generation based on previous answers
- Saves all responses to your Supabase project tied to each user
Seventeen specialized Supabase Edge Functions, one for each document type:
| Function | What it produces |
|---|---|
generate-title |
A concise project title from a description |
generate-idea |
A sharpened idea pitch based on industry + function + daily tasks |
generate-questions |
Dynamic follow-up questions for the questionnaire |
generate-answer |
AI-drafted answers for review |
generate-app-ideas |
Multiple app idea suggestions for an industry + function pair |
generate-app-outline |
Full app outline from a template |
generate-app-flow |
User flows and interaction map |
generate-requirements |
Functional and non-functional requirements |
generate-tech-stack |
Recommended tech stack with reasoning |
generate-frontend-guidelines |
Frontend design and component guidelines |
generate-backend-structure |
Backend architecture and data model |
generate-file-structure |
Recommended project file/folder layout |
generate-implementation-plan |
Step-by-step build plan |
generate-tasks |
Individual developer tasks |
generate-document |
Combine generated sections into a polished doc |
analyze-submission |
Sanity-check user input before generation |
- Save every generated project to the Projects page
- Drill into any project to see its full document set
- Access Details view with deep links to each generated section
- Update and delete projects you own
- Email + password via Supabase Auth
- Google OAuth support (optional -- configure in your Supabase dashboard)
- Password reset flow with email confirmation
- Protected routes for logged-in users
- Profile page with account information
- Enterprise DNA gradient brand colors throughout
- Responsive design (mobile-friendly from day one)
- Dark mode ready via
next-themes - Rich form controls powered by shadcn/ui + Radix
- Toast notifications via Sonner
- Smooth transitions and micro-interactions via Tailwind animations
| Layer | Technology |
|---|---|
| Framework | Vite + React 18 |
| Language | TypeScript 5 |
| UI Library | shadcn/ui + Radix UI |
| Styling | Tailwind CSS 3 |
| Icons | Lucide React |
| Database | Supabase (PostgreSQL + Row Level Security) |
| Auth | Supabase Auth (email/password + OAuth) |
| AI Runtime | Supabase Edge Functions (Deno) |
| AI Provider | OpenAI API (GPT-4o-mini by default) |
| State | Zustand + TanStack Query |
| Forms | React Hook Form + Zod |
| Routing | React Router DOM |
| Deployment | Netlify (frontend) + Supabase (backend) |
- Node.js 18+ and npm (or bun)
- A Supabase account (free tier works)
- An OpenAI API key (pay-as-you-go)
git clone https://github.com/Enterprise-DNA-OS/ai-app-idea-generator.git
cd ai-app-idea-generator
npm install- Sign in at supabase.com and click New Project
- Wait for the project to provision (~2 minutes)
- From Settings → API, copy:
- Project URL →
VITE_SUPABASE_URL - anon / public key →
VITE_SUPABASE_ANON_KEY
- Project URL →
cp .env.example .envEdit .env with your Supabase credentials:
VITE_SUPABASE_URL=https://your-project-id.supabase.co
VITE_SUPABASE_ANON_KEY=your-supabase-anon-keyInstall the Supabase CLI and link your project:
npm install -g supabase
npx supabase login
npx supabase link --project-ref your-project-idDeploy all 17 generation functions:
npx supabase functions deployAI API keys live in Supabase secrets (not in .env). Set your OpenAI key:
npx supabase secrets set OPENAI_API_KEY=sk-your-openai-keyCreate the tables the app uses. In your Supabase dashboard, open the SQL editor and create these tables (see Database Schema below), or run:
npx supabase db pushnpm run devOpen http://localhost:8080 and sign up for an account. Describe your first app idea and watch the AI generate the full spec.
AI App Idea Generator can be deployed anywhere that hosts a static Vite build.
The repo already includes a netlify.toml. Push to a GitHub repo and connect it to Netlify. Set the environment variables in Netlify's dashboard under Site settings → Environment variables.
npm run build
netlify deploy --prodnpm run build
vercel deploy --prodSet VITE_SUPABASE_URL and VITE_SUPABASE_ANON_KEY in the Vercel project settings.
npm run build produces a dist/ folder you can host anywhere:
- Cloudflare Pages
- GitHub Pages
- Any S3 + CloudFront setup
- Update environment variables in your hosting platform
- Supabase Auth settings -- Add your production domain to the allowed redirect URLs
- Google OAuth (if using) -- Add your production URL to the authorized redirect URIs in Google Cloud Console
- Enable HTTPS -- required for Supabase Auth to work correctly
- Monitor edge function logs in your Supabase dashboard
src/
App.tsx Root with providers and routing
main.tsx Entry point
components/
auth/ Auth form and modal
home/ Landing page sections (Hero, HowItWorks, Templates, etc.)
ui/ shadcn/ui primitives
ProtectedRoute.tsx Auth gate for private pages
Navbar.tsx Top navigation
Footer.tsx Footer
contexts/
UserContext.tsx Current user + loading state from Supabase
hooks/ Custom React hooks
integrations/
supabase/ Supabase client + generated types
pages/
Index.tsx Landing page
Auth.tsx Login page
Register.tsx Signup page
Questionnaire.tsx Guided questionnaire flow
Projects.tsx User project list
ProjectDetails.tsx Individual project view
GenerateDocuments.tsx Document generation page
Profile.tsx Account info
lib/ Utilities
utils/ Helper functions
types/ Shared TypeScript types
supabase/
config.toml Function configuration
functions/
_shared/ Shared OpenAI config + CORS helpers
generate-*/ 17 AI generation edge functions
analyze-submission/ Input validation
User input
→ React form submission
→ Supabase Edge Function (Deno runtime)
→ OpenAI API (GPT-4o-mini)
← Structured response
← JSON rendered in the UI + saved to Supabase
All AI calls go through Supabase Edge Functions. Your OpenAI API key lives in Supabase secrets -- it never touches the browser.
The app uses a small set of Postgres tables in Supabase:
user_projects-- One row per generated project. Stores title, description, status, and ownership (user_idFK toauth.users)questionnaire_responses-- Stores user answers to the guided questionnaire, tied to a projectgenerated_documents-- Stores AI-generated document sections (outlines, requirements, etc.) per project
Row Level Security (RLS) is enforced on every user-facing table so users only ever see their own data.
This project is designed to work well with AI development tools. Two files make this explicit:
CLAUDE.md-- Project-wide instructions, conventions, and architecture overview. Claude Code reads this automatically.AGENTS.md-- Defines specialist agents with clear ownership boundaries.
Open the project folder in Claude Code. The agent will pick up CLAUDE.md and AGENTS.md automatically and follow the conventions.
Open the project in Cursor. The CLAUDE.md file serves as context for Cursor's AI features. Use inline edit (Cmd+K) for quick changes and the chat panel for larger refactors.
Copilot picks up patterns from the existing codebase (Supabase client usage, auth checks, Tailwind conventions). The consistent conventions in CLAUDE.md make Copilot suggestions more accurate.
We encourage contributors to use AI tools. If you submit a PR:
- Mention which AI tools you used -- we see it as a positive
- Follow the conventions in
CLAUDE.md - Use the specialist agent boundaries in
AGENTS.md - Run
npx tsc --noEmitandnpm run buildbefore submitting
See CONTRIBUTING.md for detailed guidelines.
TL;DR:
- Fork the repo
- Create a feature branch (
git checkout -b feature/amazing-feature) - Make your changes (AI tools welcome)
- Run
npx tsc --noEmitandnpm run buildto verify - Commit with a descriptive message
- Push to your fork and open a PR
MIT -- use it however you want.
- Built with Claude Code by Anthropic
- Developed in Cursor -- the AI-powered IDE
- AI pair programming by GitHub Copilot
- AI generation powered by OpenAI
- Database, auth, and edge functions by Supabase
- UI components from shadcn/ui and Radix UI
- Originally released as App Idea Engine by Omni Intelligence
Built with pride by Enterprise DNA
Powered by AI-assisted development with Claude Code, Cursor, and GitHub Copilot