âš¡

Quick Start Guide

Get up and running with Outharm in 5 minutes

This guide will walk you through setting up your first content moderation project, from creating your account to making your first API call. You'll be moderating content in just a few minutes.

📋Before You Start

Account Access

You'll need an Outharm account to access the Console

Content Ready

Sample text or images to test moderation

🚀Step-by-Step Setup

1

Create Your Project

Sign in to the Console and create your first project. Projects help you organize different applications or environments.

Console Steps:

  1. Navigate to Console → Projects
  2. Click "Create Project"
  3. Enter a project name (e.g., "My App Production")
  4. Save your project
Learn more about Console →
2

Generate API Token

Create an API token to authenticate your requests. Keep this token secure as it provides access to your project.

Console Steps:

  1. Go to Console → Access Tokens
  2. Click "Generate Token"
  3. Give it a descriptive name
  4. Copy and securely store the token
Learn about API tokens →
3

Define Your Schema

Create a Schema that describes your content structure. This ensures the API knows what fields to expect in your moderation requests.

Example Schema:

📋

Blog Post Schema

T
title(Text Component)
T
content(Text Component)
I
images(Image Component)
Learn about Schemas →
4

Configure Categories

Simply enable or disable the categories you want to detect based on your platform's needs.

Simple Setup:

  • • Toggle categories on/off (sexual content, violence, hate speech, etc.)
  • • Choose what you consider harmful for your platform
Learn about Categories →
5

Make Your First API Call

Now you're ready to moderate content! Choose between automated AI moderation or manual human review.

🔌Your First API Call

🤖

Automated Moderation

Using the schema example above, here's how to make your first moderation request:

POST https://api.outharm.com/moderation/automated
Authorization: Bearer your-api-token
Content-Type: application/json

{
  "schema_id": "your-blog-post-schema-id",
  "content": {
    "title": ["Check out this awesome content!"],
    "content": ["This post contains some inappropriate material..."],
    "images": [
      "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQ...",
      "https://example.com/suspicious-image.jpg"
    ]
  }
}

Example Response (Harmful Content Detected):

{
  "submission_id": "123e4567-e89b-12d3-a456-426614174000",
  "schema_id": "your-blog-post-schema-id",
  "is_harmful": true,
  "results": {
    "title": {
      "is_harmful": false,
      "detailed": [
        { "is_harmful": false }
      ]
    },
    "content": {
      "is_harmful": true,
      "detailed": [
        {
          "is_harmful": true,
          "categories": ["sexual", "violence"]
        }
      ]
    },
    "images": {
      "is_harmful": true,
      "detailed": [
        { "is_harmful": false },
        {
          "is_harmful": true,
          "categories": ["sexual"]
        }
      ]
    }
  }
}
Learn more about automated moderation →

🚀Ready to Get Started?

Congratulations! You've successfully set up content moderation. Here are some recommended next steps to get the most out of Outharm:

🤖 Explore Automated Moderation

Learn about confidence thresholds and configuration

→

👥 Set Up Manual Review

Configure human moderation workflows

→

💻 Code Examples

Complete integration examples

→

🔗 Set Up Manual Moderation

Human review workflows and webhooks

→

Related Documentation