Signals

Signals are what make your Rules powerful. You use Signals to analyze Items and judge their characteristics. A Signal can be as simple as a basic check for a keyword or as complex as running an Item through an LLM or other AI model. A Signal takes an Item and spits out some information about the Item that you can use to make automated moderation decisions.

Cove has a library of Signals that you can use in your Rules, and each of them provides the flexibility to choose how strict or lax you want to be. For example, if your service is primarily for children, you'll want to prevent any form of nudity or sexual content. So you'll create a Rule, and in that Rule you'll choose Signals designed to detect nudity, such as nudity classifiers. If a nudity classifier Signal assigns a score of 95% to a user's profile picture (i.e. there is a 95% likelihood that the profile picture contains nudity), then you might have your Rule automatically ban the user.

Our Signals library contains three types of Signals:

1. Custom AI Models: If you create custom AI models in Cove, each model will be available for us in the Signals library.
2. Text Analysis: We offer a number of Signals to run analysis on text, including
   1. Exact Keyword Matching: Look for exact words or phrases in your content.
   2. Regular Expression (Regex) Matching: Look for text patterns in your Items using regular expressions.
   3. Text Variant Matching: We've built an algorithm to detect common variants of strings of text. This is particularly useful to catch bad actors trying to evade your enforcement by using leetspeak, replacing characters, adding punctuation in the middle of words, or other forms of evasion. For example, if you're looking for the word "Hello", we'll detect "h3||0" and "helllllllloooo" as matches.
   4. Language Detection: Given some text, we can detect what language it contains. Often the exact language of the text is difficult to discern - particularly when a piece of text contains more than one language. In these cases, we choose the highest probability language.
3. 3rd Party Integrations: Connect to any other Trust & Safety API at the click of a button. We've built integrations with those companies' APIs so you don't have to.
4. Location Matching: If you want to set up Rules that target specific locations, you can do so with our location matching Signal. With every Item you send us, you'll need to include a geohash representing the latitude-longitude location of the user who created it. Then you can create Rules that only action on Items created in or around particular locations. You can even create Matching Banks that contain geohash locations, so you can easily manage a large set of locations in one place.
5. Custom Signals: you can add any custom signal! If you've built your own machine learning models or have some internal data that Cove can't access, but you'd like to reference it in your Rules, you can expose it in a secure, privacy-safe way.