YouTube Introduces AI‑Powered Custom Feeds, Letting Users Craft Their Own Recommendation Algorithms

How the Feature Operates

YouTube’s new “custom feeds” let users type a free‑form description of the video mix they want. The prompt is processed by Google’s Gemini AI, which curates a stream of videos matching the request. The resulting feed appears as a dedicated tab pinned to the top of the YouTube home page, allowing immediate access without navigating the standard recommendation list.

Why YouTube Is Adding This Now

“One of the amazing things about being on YouTube is that the world is always at your fingertips,” said Emily Moxley, VP of Product Management for Viewer AI, during a pre‑brief before the Made On YouTube event. “There’s over 20 billion videos in the YouTube corpus, so you’re always one search away from a treasure trove of topics.”

The company argues that the tool will help users sift through the massive catalog and jump straight to a feed that matches a specific mood, commute length, or interest. The feeds are additive, not substitutive; the original recommendation feed remains unchanged.

Competitive Landscape: Other Platforms Already Offer Similar Tools

The idea of user‑driven algorithmic feeds is not new. Bluesky popularized it years ago to differentiate from X, and this year launched Attie, an AI assistant for feed creation. Meta’s Threads, Instagram, X, and Spotify have each rolled out comparable features, many also powered by artificial intelligence.

What Users Can Expect

Support for multiple custom feeds will begin rolling out next month on both web and mobile versions of YouTube. Users can craft distinct feeds for different scenarios—such as a 30‑minute train commute playlist of video podcasts or a collection of calming commentary videos for unwinding—while the main recommendation feed continues to operate in the background.