YouTube has unveiled a new feature called custom feeds, allowing users to describe in their own words the kinds of videos they’d like to see recommended to them. The feature leverages Google’s Gemini AI model to build a feed around your request, making it easier to curate content based on specific interests or moods. For instance, you could create a feed of video podcasts to watch during your train commute or a feed of ‘relaxing commentary videos to unwind with’.

The addition of custom feeds follows similar moves by other social networks, such as Bluesky’s Attie, Meta’s Threads and Instagram’s Explore tab. Spotify has also launched a feature that allows users to create their own playlists based on their preferences.

Emily Moxley, VP of Product Management for Viewer AI at YouTube, believes this feature will help users better explore the vast number of videos hosted on the platform. ‘There’s over 20 billion videos in the YouTube corpus, so you’re always one search away from a treasure trove of topics,’ she stated.

The new feeds will not replace YouTube’s main feed, which features all your recommendations. Instead, users will be able to easily hop into whichever feed best suits their needs when they open the YouTube app. Support for creating multiple custom feeds will roll out across YouTube on web and mobile, starting next month.