This is very exciting, thanks for sharing Mike! I can't wait to try the dev trial!
Can you comment on whether you expect this to rely on closed source components / models? What is the thinking regarding a public eval suite? Thanks, Rick On Thu, Oct 1, 2026 at 1:04 PM Mike Wasserman <[email protected]> wrote: > Contact emails > > [email protected], [email protected] > > Explainer > > https://github.com/explainers-by-googlers/decisions-api > > Specification > > No information provided > > Summary > > Provides high-speed, deterministic semantic decision-making directly on > the user's device as a built-in AI capability. > > Unlike open-ended generative language models (such as the Prompt API) that > decode text token-by-token over hundreds or thousands of milliseconds, the > Decisions > API (window.DecisionModel) evaluates natural language input text against > a structured set of questions and candidate options in a single forward > pass using logit scoring. This delivers micro-latency evaluations (tens > or low hundreds of milliseconds on typical consumer laptop CPUs and GPUs) > while outputting calibrated confidence values. > > This brings non-autoregressive "System 1" decision models (e.g. Jev > <https://typesafe.ai/blog/introducing-system-one-models-and-jev>, Laya > <https://huggingface.co/convaiinnovations/laya>, Kev > <https://github.com/jaredpalmer/kev>, Open-Jev > <https://github.com/kyegomez/open-jev>) natively into the web platform, > providing developers with a pragmatic, zero-marginal-cost "Semantic If" > primitive for real-time client-side routing, interactive input guardrails, > and adaptive user interfaces. > > Blink component > > Blink>AI > <https://issues.chromium.org/issues?q=customfield1222907:%22Blink%3EAI%22> > > Web Feature ID > > Missing feature > > Motivation > > Web applications and agentic workflows increasingly need to make fast, > structured decisions over unstructured input and page state: Which search > filters match this natural-language query? Which UI action or tool fulfills > the user's goal? Would this draft trigger a moderation review or miss key > details before submission? What does this page section or form field > represent? [1] > > Without a built-in decision primitive, developers are forced to choose > between several suboptimal alternatives [2]: > > > 1. > > Brittle Heuristics: Keyword rules and regular expressions that are > fast and local, but break on phrasing variations, typos, and multilingual > input. > 2. > > Bespoke Model Selection & Training Tax: For most web products, > curating training data, evaluating models, integrating runtimes, and > bundling multi-megabyte model weights is a prohibitive operational hurdle. > Users also face downsides of duplicating network and storage costs, and > unmanaged resource contention across origins. > 3. > > Cloud AI Endpoints: Capable, but introduces hundreds of milliseconds > network round trips, triggers privacy tradeoffs by transmitting user drafts > off-device, and incur recurring or high-frequency cloud / server costs. > 4. > > Generative LLMs (LanguageModel): Autoregressively generating > structured JSON via client-side LLMs is 10–50x heavier than necessary, > consumes significant battery/RAM, and lacks calibrated option > probabilities. > > > Recent advancements demonstrate that compact, non-autoregressive decision > models can evaluate candidate choices in tens of milliseconds with > calibrated confidence distributions. We believe Built-in AI has a natural > role to play: by offering a platform-level decision engine, we can make > fast semantic branching an ubiquitous primitive. Web applications gain > instant access to binary verification, categorical routing, and ordinal > scoring tasks with amortized overheads, on-device privacy, and efficient > hardware utilization. > > This prototype phase aims to confirm whether the community's enthusiasm > translates into concrete web production use cases and architectural > viability. > > [1]: https://github.com/explainers-by-googlers/decisions-api#use-cases > > [2]: > https://github.com/explainers-by-googlers/decisions-api#considered-alternatives > > > Initial public proposal > > https://github.com/webmachinelearning/proposals/issues/20 > > Goals for experimentation > > For the initial DevTrial behind chrome://flags/#decisions-api, we are > intentionally starting with a minimal viable surface focused on common > decision evaluations. This allows us to validate core latency, ergonomics, > and accuracy on key client-side routing scenarios first. > > We will use early developer and ecosystem feedback to iterate on the API > shape, optimize runtime performance and model quality, and determine which > additional capabilities warrant graduation into subsequent milestones. > > Requires code in //chrome? > > True > > Tracking bug > > https://issues.chromium.org/issues/568193538 > > Measurement > > Use counters will track API adoption: DecisionModel_Availability, > DecisionModel_Create, and DecisionModel_Evaluate. > > Estimated milestones > > 157 > > Link to entry on the Chrome Platform Status > > https://chromestatus.com/feature/5155080092385280?gate=5985020782182400 > > -- > You received this message because you are subscribed to the Google Groups > "blink-dev" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to [email protected]. > To view this discussion visit > https://groups.google.com/a/chromium.org/d/msgid/blink-dev/CAEsbcpXXn_B5zCUpLgAtg8wRZpLJhfXtdVH%2Bc80uOcGjt1s%3Dpg%40mail.gmail.com > <https://groups.google.com/a/chromium.org/d/msgid/blink-dev/CAEsbcpXXn_B5zCUpLgAtg8wRZpLJhfXtdVH%2Bc80uOcGjt1s%3Dpg%40mail.gmail.com?utm_medium=email&utm_source=footer> > . > -- You received this message because you are subscribed to the Google Groups "blink-dev" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion visit https://groups.google.com/a/chromium.org/d/msgid/blink-dev/CAFUtAY_V%2Bb49X-_zPvp1WTG_8JxW6vThB%3DOvXjeUq7xQfQB-PA%40mail.gmail.com.
