YouTube launches Custom Feeds letting users write prompts to shape their homepage
Google unveiled Custom Feeds at its Made on YouTube event, a feature letting users type natural-language requests to generate a personalized homepage feed. The tool uses large language models to interpret prompts like genre or mood combinations and build a matching set of video suggestions. YouTube tested the feature earlier this year and plans a full rollout to all US users across mobile, desktop and TV.
GoKawiil's interpretation of the reporting above, not reported fact.
Giving users direct, language-based control over recommendations marks a shift from passive signals like likes and watch history toward explicit user steering of algorithmic feeds. YouTube VP Emily Moxley frames this as a response to user demand for more control, which could reduce reliance on opaque algorithmic guesswork and increase user trust. It may also set a precedent for other platforms to offer similar prompt-based personalization tools.
- YouTube's Custom Feeds lets users type natural-language prompts to build a personalized homepage.
- The feature uses large language models and was tested earlier in 2025 before wider rollout.
- YouTube plans to make it available to all US users on mobile, desktop, and TV soon.
Source: wired.com — Reece Rogers, 2026-09-23
Published there as: “YouTube’s Custom Feeds Give You More Control Over the Algorithm”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.