Feed AI Content Filter

Describe what you want to hide in natural language and a browser extension masks it in real time

Problem

Social media and news feeds are full of ragebait, political arguments, and clickbait. Users want a customizable filter based on their own wishes, but existing blockers only support keywords and can't understand semantics — hiding "content that makes me angry" is nearly impossible with keyword rules.

Solution

A browser extension with a built-in AI classifier lets users write rules in natural language (e.g. "hide political content", "hide anxiety-inducing news"). The extension semantically judges each feed post before render and hides matches directly. Supports per-site rule switching and shareable rule packs.

Users

Heavy social media users among knowledge workers, users sensitive to information quality, people who want to filter out certain content for focus

MVP

Content hiding on major feed sites; multiple user-created natural-language filter rules; local lightweight model or user-provided API key for semantic classification; one-click review and temporary undo of hidden items

Revenue

Free extension with a subscription premium tier for cross-device sync, more site templates, and cloud rule compilation; or a one-time purchase

Why now

Feed quality anxiety keeps rising, browser extensions have low distribution cost, and indie developers can validate fast; big platforms won't build user-defined semantic filtering