=== AI-Powered Comment Moderator ===
Contributors: andreis
Donate link: https://aivisualtales.com/
Tags: comments, moderation, AI, spam filter, automatic moderation
Requires at least: 6.4
Tested up to: 6.7
Requires PHP: 7.4
Stable tag: 1.0
License: GPLv2 or later
License URI: https://www.gnu.org/licenses/gpl-2.0.html

AI-powered comment moderation to automatically filter spam, toxicity, and inappropriate content.

== Description ==

AI Comment Auto-Moderator helps you automatically moderate comments using **artificial intelligence**.

?? **Reduce spam & offensive comments effortlessly with AI!**

== Installation ==

1. **Upload via Admin Panel:**
   - Go to **Plugins ? Add New**.
   - Click **Upload Plugin** and select the plugin ZIP file.
   - Click **Install Now** and then **Activate**.

2. **Manual Installation:**
   - Download the plugin and unzip it.
   - Upload the `ai-comment-moderator` folder to `/wp-content/plugins/`.
   - Activate the plugin from the **Plugins** menu in WordPress.

3. **Setup AI API Key (Required):**
   - Go to **Settings ? AI Moderator**.
   - Enter your **OpenAI API Key** (or other supported AI provider).
   - Adjust moderation settings based on your needs.

4. **You're Ready to Go!**
   - AI will now automatically analyze and moderate new comments.

== External Services ==

This plugin connects to the OpenAI API to perform automated comment moderation and AI-powered analysis. It uses OpenAI's **GPT-4** and **Moderation API** to classify and filter comments for inappropriate content, spam, or harmful language.

=== What data is sent and when? ===

- When a user triggers AI moderation (e.g., clicking the **Run AI** button), the comment content is sent to OpenAI's API for processing.
- Depending on the moderation method, the request may include:
  - The comment text being analyzed.
  - AI model settings such as `gpt-4-turbo` or `Moderation API`.
  - A predefined system prompt (if applicable).
- OpenAI processes the request and returns a moderation decision, including a **confidence score and category classification**.

=== Why is this data sent? ===

The data is sent to OpenAI for **automated content moderation**. OpenAI’s AI models classify comments into categories such as:
- **Spam**
- **Hate Speech**
- **Inappropriate Language**
- **Nonsensical Content**
- **Safe/Allowed Content**

The plugin does not store or share this data beyond the **API request** itself.

=== Where is this data sent? ===

This plugin makes **HTTP requests** to the following OpenAI API endpoints:

- `https://api.openai.com/v1/chat/completions`  
  (Used in `includes/chatgpt.php:43` and `includes/moderation.php:104` to process comment content via ChatGPT)
  
- `https://api.openai.com/v1/moderations`  
  (Used in `includes/moderation.php:47` to analyze comment text with OpenAI's Moderation API)

All requests are **sent securely using HTTPS**, and the OpenAI API key is required for authentication.

=== Under what conditions is the data sent? ===

- The plugin **only sends data when a user explicitly triggers AI moderation**.
- The site administrator **must provide an OpenAI API key** for the service to function.
- The OpenAI API key is stored securely in the WordPress database and is **never shared or logged** by the plugin.

=== OpenAI Service Information ===

- OpenAI API Terms of Use: [https://openai.com/terms](https://openai.com/terms)
- OpenAI Privacy Policy: [https://openai.com/privacy](https://openai.com/privacy)
- OpenAI Moderation API: [https://platform.openai.com/docs/guides/moderation](https://platform.openai.com/docs/guides/moderation)
- OpenAI Chat API: [https://platform.openai.com/docs/guides/gpt](https://platform.openai.com/docs/guides/gpt)


== Frequently Asked Questions ==

= How does AI moderation work? =
The plugin uses an AI-powered API to analyze each comment, determine if it's spam or inappropriate, and take action accordingly (flag, approve, delete).

= Does it require an API key? =
Yes, you need an **OpenAI API key** or another supported AI provider for the plugin to function.

= Can I customize moderation settings? =
Yes! You can fine-tune **AI confidence levels**, moderation rules, and even create **custom prompts** for the AI.

= Is this plugin GDPR compliant? =
Yes, the plugin does not store personal data. It sends only the comment text for analysis and does not collect any user information.


== Changelog ==

= 1.0.0 =
- Initial release with AI-powered comment moderation.
- AI spam filtering, confidence scores, and moderation dashboard.

== License & Credits ==

This plugin is released under the **GPL v2 or later**. AI services used are provided by **OpenAI**, and their API terms apply.

 **Developed by Andrea Bocchetti