Veritas AI Moderation 1.3.2

Veritas AI is a content moderation add-on for XenForo designed to make community management easier. Using a sophisticated multi-model AI system, it automatically detects and flags harmful content like spam and toxicity with a high degree of accuracy. Instead of spending hours on manual review, moderators can shift their focus from policing to actively engaging with and growing the community.

Disclaimer on Pricing: While this add-on is free to download, and a free trial API key is available to get you started, a recurring API usage fee is associated with its continued use. Please contact Audentio directly for more information about API usage.

Product demo: You can try out a product demo here.

Here’s how it works

When a new post is created on the forum, the contents of the post are scored based on how likely the post is to be spam content or toxic content. If either of these are flagged, the post gets triaged, and then added to the log. So what happens next? That depends on the user who posted it, why it was flagged, and how you choose to configure the add-on. For forums we manage, here’s how we set it up:

Spam

If you’re a new user, we send the post to the approval queue to be reviewed by a moderator. If the model is really confident, we ban the user as well so that they don’t make more spam content.
If you’re an existing trusted user, your post is silently reported. The moderation team can then choose to take action, or to ignore.

Toxicity

If a post scores 80% confidence or higher on toxicity, we report the post silently.
If a post scores 90% or higher on toxicity, we send the post to the approval queue.


However, you can choose to set your site up differently. If you want to ignore specific groups, you can. If you want all flagged posts to go to the approval queue, you can do that too. And if you want to place it safe and have all posts silently reported (but never removed), you have that option as well.

Benefits of Using Veritas

Reduces Barriers to Entry: Veritas AI can selectively moderate new users, so you no longer need to require post approval for all new members, making it easier for legitimate users to join and participate.
Saves Moderator Time: Spend less time searching for problematic content. The add-on flags posts for you, allowing moderators to focus on triaging reported content.
Increases Speed of Moderation: Automatically removes or flags harmful content within a minute of it being posted, significantly faster than manual detection.
Scalability: As your community grows, Veritas AI handles the increasing volume of content without requiring a corresponding increase in your moderation team's workload.

Features

• Flexible Moderation Actions: Supports multiple actions on flagged content, including silently reporting posts to moderators or sending them to the approval queue. These actions can be applied to specific user groups.
• Comprehensive Content Support: Protects your community by scanning posts, private messages, and profile posts.
• Auto-banning: Can be configured to automatically ban users for posting spam (disabled by default).
• Granular Controls: Easy-to-use controls allow you to adjust the sensitivity of the AI to make it more or less aggressive in flagging content.
• Targeted Moderation: Exclude specific forums or user groups from being scanned by Veritas AI.
  Detailed Content Logging: Provides a full content log showing how each post was scored, the reason for the score, and any subsequent moderator actions.