AWS’s new decision model comes with a familiar address. Released October 1, Strands Decider 2B is an open-weight model built on Alibaba’s Qwen3.5. But run it as a server, and it answers at /v1/systemone — the same endpoint startup TypeSafe AI introduced with Jev just over two weeks earlier.

Within three weeks, decision models went from one startup’s experiment to a category. OpenAI, Upstage, Perplexity and Cloudflare offer hosted decision models, while AWS and independent developers have published open weights on Hugging Face. What’s standardizing fastest is TypeSafe’s schema — the structure of the request and response — even when vendors publish it under their own URLs and endpoints.

LLM developers saw a similar process unfold. OpenAI’s Chat Completions API became the default interface for LLMs because so many providers cloned it. OpenAI later launched Open Responses, an open specification based on its Responses API. That history suggests a possible trajectory rather than a settled outcome.

A decision model takes application state, such as a customer message and the relevant policy, along with a set of typed questions. It returns structured answers with a probability attached to each option, and it never writes prose, code, or explanations of its reasoning. TypeSafe calls Jev a System One model, borrowing a term psychologist Daniel Kahneman popularized for fast, intuitive judgment

The System One API reduces every decision to three question types. A choice question selects one option from a list, and a score question places the input on an ordered rubric. A noul (yes/no) question returns the probability that a yes-or-no condition holds, and developers can mix all three types in one request.

Source link