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.
