Quick Start

Quick Start

Get Manuscript running and detecting AI content in under 30 seconds.

Option 1: Docker (Recommended)

The fastest way to get started:

docker run -p 8080:8080 manuscript/manuscript

That’s it! The API is now running at http://localhost:8080.

Option 2: Go Install

If you have Go 1.21+ installed:

go install github.com/vinpatel/manuscript/cmd/api@latest
manuscript

Option 3: Build from Source

git clone https://github.com/vinpatel/manuscript.git
cd manuscript
make run

Verify It’s Working

Check the health endpoint:

curl http://localhost:8080/health

You should see:

{"status": "healthy", "version": "0.2.0"}

Detect AI Content

Text Detection

curl -X POST http://localhost:8080/verify \
  -H "Content-Type: application/json" \
  -d '{"text": "Your content to analyze here..."}'

Response:

{
  "id": "hm_abc123",
  "verdict": "human",
  "confidence": 0.87,
  "content_type": "text",
  "signals": {
    "sentence_variance": 0.42,
    "vocabulary_richness": 0.78,
    "contraction_ratio": 0.15
  },
  "processing_time_ms": 8
}

Image Detection

curl -X POST http://localhost:8080/verify \
  -F "image=@photo.jpg"

Audio Detection

curl -X POST http://localhost:8080/verify \
  -F "audio=@recording.mp3"

Video Detection

curl -X POST http://localhost:8080/verify \
  -F "video=@clip.mp4"

Understanding the Response

Field	Description
id	Unique identifier for this analysis
verdict	"human" or "ai"
confidence	0.0 to 1.0 confidence score
content_type	Type of content analyzed
signals	Detailed breakdown of detection signals
processing_time_ms	Time taken to process

Detailed Analysis

Add ?detailed=true for comprehensive signal breakdown:

curl -X POST "http://localhost:8080/verify?detailed=true" \
  -H "Content-Type: application/json" \
  -d '{"text": "Your content here"}'

Next Steps

• Installation Guide - Production deployment
• API Reference - Full API documentation
• Text Detection - How text detection works