Skip to content

QUICKSTART.md

Latest commit

 

History

History
169 lines (116 loc) · 3.72 KB

QUICKSTART.md

File metadata and controls

169 lines (116 loc) · 3.72 KB

Quick Start Guide

Get the Slop Detector running in 5 minutes.

Prerequisites

  • Node.js 18+ installed
  • npm or yarn
  • Terminal/Command line

Step 1: Install Backend Dependencies

cd backend
npm install

Step 2: Start Backend Server

npm run dev

You should see:

⛅️ wrangler 3.x.x
------------------
[wrangler:inf] Ready on http://localhost:8787

Keep this terminal open.

Step 3: Install Frontend Dependencies

Open a new terminal window:

cd frontend
npm install

Step 4: Configure Frontend

cp .env.example .env

The default configuration points to http://localhost:8787 which should work with the backend running locally.

Step 5: Start Frontend

npm run dev

You should see:

  VITE v5.x.x  ready in xxx ms

  ➜  Local:   http://localhost:3000/

Step 6: Open Browser

Navigate to: http://localhost:3000

Step 7: Test the Tool

  1. Paste some text into the textarea (minimum 100 characters)
  2. Click "Analyze Text"
  3. View the results showing:
    • Classification (AI-generated, Mixed, or Human-written)
    • Confidence score
    • Detected patterns
    • Metadata

Example Test Text

Try this AI-like text:

I hope this helps! Let me know if you need anything else. It's important to note
that this stands as a testament to the capabilities of modern systems. As an AI
language model, I can provide assistance with various tasks. Would you like me
to explain further? Here's a comprehensive overview of the topic.

This should score high for AI-generated content due to multiple collaborative phrases and AI self-references.

Example Human Text

Try this human-written text:

I went to the store yesterday and bought some groceries. The weather was nice,
so I decided to walk instead of driving. On my way home, I ran into an old
friend from college. We grabbed coffee and caught up for about an hour. It was
really great to see them again after all these years.

This should score low for AI-generated content.

Testing the API Directly

You can also test the backend API directly:

curl -X POST http://localhost:8787/api/analyze \
  -H "Content-Type: application/json" \
  -d '{"text":"I hope this helps! Let me know if you need anything else. As an AI language model, I can assist with various tasks."}'

Troubleshooting

Backend won't start

  • Make sure you're in the backend/ directory
  • Run npm install again
  • Check Node.js version: node --version (should be 18+)

Frontend won't connect to backend

  • Make sure backend is running on port 8787
  • Check .env file has correct VITE_API_URL
  • Look for CORS errors in browser console

Port already in use

If port 3000 or 8787 is already in use:

Backend: Edit wrangler.toml to change port Frontend: Vite will automatically use next available port

What's Next?

  • Read the full README.md for complete documentation
  • Check IMPLEMENTATION_SUMMARY.md for technical details
  • Explore the pattern registry in backend/src/patterns/registry.ts
  • Review the OpenSpec proposal in openspec/changes/add-ai-detection-tool/

Development Commands

Backend

cd backend
npm run dev      # Start dev server
npm run deploy   # Deploy to Cloudflare Workers
npm test         # Run tests (when implemented)
npm run lint     # Run ESLint

Frontend

cd frontend
npm run dev      # Start dev server
npm run build    # Build for production
npm run preview  # Preview production build
npm run lint     # Run ESLint

Production Deployment

See README.md for deployment instructions to Cloudflare Workers and Cloudflare Pages.

Questions? Check the documentation or open an issue!