Our tool works by:

• Detecting abusive language in messages and posts across platforms.

• Warning users when potentially harmful content, such as sensual images, is detected.

• Censoring harmful texts before they can be read, to ensure a safer environment.

• Providing personalized tips to help users deal with harassment.

Our algorithm scans every incoming message or post for profane, abusive, or harmful language. We’ve created a robust dictionary of offensive terms, and as users receive messages, each word is checked and compared to this list. If harmful language is detected, the tool either alerts the user or censors the text, preventing harmful content from being seen.

Using advanced image recognition, we can detect sensual or explicit images being shared through platforms. If such content is found, a warning is issued to the user with the option to either block the sender or report the incident. This prevents unsolicited, inappropriate images from appearing in your feed.

In some cases, the tool will censor harmful texts completely before they reach the recipient’s view. This helps to prevent trauma or distress caused by disturbing language.

Initially, our tool supports English and Mongolian—two languages that are critical in the regions we aim to serve. As we grow, we plan to expand language support to ensure the safety of women across the globe.