YouTube announced a prompt-based feature called custom feeds on Wednesday that allows viewers to describe the specific videos they want recommended, as reported by Ars Technica.
The tool relies on Google's Gemini artificial intelligence model to turn text descriptions into dedicated recommendation feeds. Viewers enter requests into a prompt box, specifying topics, exclusions, or formats, such as video podcasts for a 30-minute train commute or relaxing commentary videos. People can supply detailed instructions outlining what content to prioritize and what to filter out.
The interface places each generated feed into an individual tab pinned to the top of the YouTube home page. These custom tabs will exist alongside the standard recommendation stream rather than replacing the platform's default feed.
Emily Moxley, vice president of product management for Viewer AI at YouTube, detailed the platform's scale ahead of the Made On YouTube event on Wednesday. “One of the amazing things about being on YouTube is that the world is always at your fingertips,” Moxley said. “There’s over 20 billion videos in the YouTube corpus, so you’re always one search away from a treasure trove of topics.”
The move follows similar feed-customization mechanisms across social networks. Decentralized platform Bluesky popularized user-created feeds before rolling out an AI feed-building tool named Attie this year. Meta's Instagram and Threads platforms, along with X and Spotify, have likewise launched comparable feed-creation tools.
YouTube plans to begin rolling out support for multiple custom feeds next month across its desktop website and mobile applications.
