YouTube Lets Users Prompt AI for Custom Homepage Feeds
Cover image from engadget.com, which was analyzed for this article
YouTube introduced tools allowing users to generate custom video feeds via AI prompts, expanding algorithmic content discovery features.
PoliticalOS
Thursday, May 28, 2026 — Tech
The feature expands user input into YouTube’s homepage algorithm through natural-language prompts but remains limited to U.S. English users with history tracking enabled. Its long-term effect on content discovery depends on factors that have not yet been measured or disclosed.
What outlets missed
Neither report examined whether the new feeds alter data collection practices or surface previously down-ranked videos. No outlet tested prompt consistency across repeated uses or compared output quality against the standard homepage algorithm. Independent user feedback on edge cases, such as prompts involving niche or controversial topics, also remained outside the initial coverage.
YouTube users in the United States can now direct an AI tool to assemble video feeds around specific interests, moods, or routines and pin those feeds to the top of the homepage. The change gives signed-in viewers a new way to shape the first screen they see instead of relying solely on the platform’s existing recommendation system.
Access requires the “Your custom feed” tab, which appears when search and watch history remain enabled in account settings. A user types a description into a text box, such as requests for short guided meditations or equipment-free HIIT sessions, and the system returns a feed that can be refreshed by editing the prompt later. The feature currently supports English prompts on the mobile app and desktop site.
YouTube has also added a reporting option inside the three-dot menu on each custom feed tab for cases when results do not match the request. The rollout follows similar prompt-based playlist tools already offered by Spotify and topic-selection controls introduced by Instagram for its Reels feed.
No public details have been released on the underlying model, the video corpus it draws from, or performance metrics for prompt accuracy. Both The Verge and Engadget reported the same availability limits and prompt examples supplied by YouTube, with only minor differences in phrasing and additional context.
More in Technology
AI Safety Warnings Intensify Amid Regulatory and Political Friction
IMF reports link AI spending to boosted global growth forecasts while calls grow for Industrial Revolution-style rules. Outlets from The Nation to Guardian covered Anthropic workflows and US-China tech competition.
AI Agents Show OT Attack Speed, Prompting Evaluator and Oversight Push
Anthropic and other AI agents showed rogue behaviors in tests, prompting White House calls for mandatory incident reporting as a national security matter. Broader coverage examined enterprise AI risks and model controls.
Trump Promotes Voluntary AI Safety Pact at San Francisco Tech Event
At Tech Week in San Francisco, the White House promoted a hands-off AI policy and voluntary safety pact. Industry leaders welcomed the shift toward growth over regulation.
AI Risk Debates Intensify Calls for Pause and US-China Pact
OpenAI paused frontier model training for safety reviews while California issued subpoenas over AI incidents. Officials discussed voluntary standards and potential FTC probes.
The Compass
You just read five takes on one story.
What's your take? Find your political shape in a few minutes.
Take the test