{"id":394653,"date":"2026-05-06T13:41:29","date_gmt":"2026-05-06T19:41:29","guid":{"rendered":"https:\/\/css-tricks.com\/?p=394653"},"modified":"2026-05-06T14:04:48","modified_gmt":"2026-05-06T20:04:48","slug":"googles-prompt-api","status":"publish","type":"post","link":"https:\/\/css-tricks.com\/googles-prompt-api\/","title":{"rendered":"Google\u2019s Prompt API"},"content":{"rendered":"\n

Mat Marquis<\/a> on Google pulling the web standards equivalent of U2 album marketing<\/a>:<\/p>\n\n\n\n

\n

As a Chrome user, you\u2019ll have received Gemini Nano in the form of a 4GB transfer<\/a> recently; no permission asked or required. If you remove it, Chrome will re-download it. For reasons I can only guess at<\/a>, Gemini Nano is presumably now considered to be part of Chrome itself, despite being a standalone product that is included alongside but not integrated into<\/em> the browser \u2014 the way a copy of Bonzi Buddy<\/a> included in a browser update might be considered a part of said browser.<\/p>\n<\/blockquote>\n\n\n\n\n\n\n\n

It’s not exactly new<\/em> news, as we’ve had published<\/a> explainers<\/a> on it for over a year now, as well as an intent to prototype<\/a> for just as long.<\/p>\n\n\n\n

Mozilla has already voiced its concerns\/opposition<\/a>:<\/p>\n\n\n\n

\n

According to Chrome’s documentation<\/a>, to use the prompt API you must ‘acknowledge’ Google’s Generative AI Prohibited Uses Policy<\/a>. Elements of this policy go beyond law. For example:<\/p>\n\n\n\n

\n

Do not engage \u2026 generating or distributing content that facilitates \u2026 Sexually explicit content
Do not engage in misinformation, misrepresentation, or misleading activities. This includes \u2026 Facilitating misleading claims related to governmental or democratic processes<\/p>\n<\/blockquote>\n\n\n\n

This seems like a bad direction for an API on the web platform, and sets a worrying precedent for more APIs that have UA-specific rules around usage.<\/p>\n<\/blockquote>\n\n\n\n

I have nothing to add, only that this is the sort of thing that seems worth knowing. Mat’s take-home isn’t exactly comforting because, remember, this has already shipped<\/em>:<\/p>\n\n\n\n

\n

I\u2019d like to say that something to the tune of \u201ctheir whole argument hinges on \u2018positive developer sentiment,\u2019 so let\u2019s show them that there isn\u2019t any\u201d \u2014 but there isn\u2019t any; they cited<\/em> places where there isn\u2019t any. That\u2019s not how it works for them. Google participates in the web standards process the way a bear participates in the \u201ccamping\u201d process.<\/p>\n\n\n\n

[…]<\/p>\n\n\n\n

Remember this the next time Google announces an \u201cexciting new standard\u201d that they\u2019re heroically championing \u2014 for you, for users, for good of the web \u2014 in language that has just a hint of inevitability about it.<\/p>\n<\/blockquote>\n\n\n\n

The browser ecosystem<\/a> has historically provided us with plenty of concerns. Alex Russell’s writing<\/a> is a treasure trove of the current limits of browser choice. And things are especially murky when we need to be reminded that not all browser APIs are Web APIs<\/a><\/em>.<\/p>\n\n\n\n

Maybe helpful, maybe not:<\/p>\n\n\n\n

\"Chrome<\/figure>\n\n\n\n

More coverage, if you’d like:<\/p>\n\n\n\n