[w3ctag/design-reviews] Prompt API (Issue #1093)

domenic created an issue (w3ctag/design-reviews#1093)

こんにちは TAG-さん!

I'm requesting an early TAG design review of the Prompt API.

This is a JavaScript API for directly prompting an AI language model, including text, image, and audio inputs.

Although the Chrome built-in AI team is exploring purpose-built APIs for some use cases (#948, #991), we are also exploring a general-purpose "prompt API" which allows web developers to prompt a language model directly. This gives web developers access to many more capabilities, at the cost of requiring them to do their own prompt engineering.

  - Explainer: https://github.com/webmachinelearning/prompt-api/blob/main/README.md
  - User research: none (although we have [developer-facing research](https://docs.google.com/presentation/d/1DhFC2oB4PRrchavxUY3h9U4w4hrX5DAc5LoMqhn5hnk/edit#slide=id.g349a9ada368_1_6327))
  - Security and Privacy self-review: https://github.com/webmachinelearning/prompt-api/blob/main/security-privacy-questionnaire.md
  - GitHub repo: https://github.com/webmachinelearning/prompt-api
  - Primary contacts:
      - Domenic Denicola (@domenic), Google, spec editor
      - Etienne Noël (@etiennenoel), Google, team lead
  - Organization/project driving the design: Google
  - This work is being funded by: Google, Microsoft
  - Incubation and standards groups that have discussed the design:
    - This API has been discussed at the majority of Web Machine Learning CG meetings in 2025, the minutes for which can be found at https://github.com/webmachinelearning/meetings/tree/main/telcons
  - Standards group(s) that you expect to discuss and/or adopt this work when it's
    ready: W3C Machine Learning Working Group
  - Multi-stakeholder feedback:
    - Chromium comments: prototyping
    - Mozilla comments: https://github.com/mozilla/standards-positions/issues/1213 and some comments in the Web ML CG minutes listed above
    - WebKit comments: https://github.com/WebKit/standards-positions/issues/495
    - Developer comments: some of them are collated in https://github.com/webmachinelearning/prompt-api/blob/main/README.md#stakeholder-feedback
  - Major unresolved issues with or opposition to this design: There are a lot of enhancement requests on [the issue tracker](https://github.com/webmachinelearning/prompt-api/issues). There are a couple of interop concern issues there as well. It all seems manageable at this point, though.
  - [x] I have reviewed the TAG's [Web Platform Design Principles](https://www.w3.org/TR/design-principles/)

You should also know that...

Although this feature exposes an on-device language model, the language model is never trained on, and does not have access to, any local user-specific data. (Sometimes people seem to be confused by this, so we're trying to include this disclaimer in as many places as possible.)

-- 
Reply to this email directly or view it on GitHub:
https://github.com/w3ctag/design-reviews/issues/1093
You are receiving this because you are subscribed to this thread.

Message ID: <w3ctag/design-reviews/issues/1093@github.com>