Amazon Launches Its Own Jev Clone as Decision Models Flood the Web

Amazon Web Services has launched an open-source decision model inspired by TypeSafe’s Jev, as AI developers increasingly prioritize intelligence optimized for computer automation over frontier large language models.

Released the same week OpenAI announced a similar offering, Amazon’s Strands Decider 2B provides a high-speed, low-cost method for sorting pre-decided options while delivering confidence scores for its choices. The model is fully open-sourced, immediately available, and compact enough to run locally.

Amazon distinguished engineer Marc Brooker initiated the project after observing Jev and attempting to build a similar model. The homebrew project proved successful—briefly topping the Jevbench rankings for its size—prompting Amazon engineers to refine it and release it through Strands Labs, a division focused on developing tools and protocols for deploying AI agents.

Brooker explains that the demand for such a tool arose from discussions with AWS customers, whose agentic workflows often do not require the capability or expense of a fully-featured LLM at all times.

“What originally piqued my interest in this class of models was that they make a perfect decider for a workflow step— ‘what is the next thing for me to do here, based on where I am?’” Brooker told TechCrunch. He noted that this offers customers “a workflow step that can be structured in a way that is more reliable, thanks to the confidence scores, thanks to the closed domain of answers, [and is] lower latency, potentially lower cost.”

Like other decision models, Strands Decider is built on the “torso” of an LLM, specifically Qwen3.5-2B, but instead of generating text, it outputs calibrated choices. TypeSafe named their model Jev after economist William Stanley Jevons, invoking his theory that the falling cost of something—such as computer intelligence—can actually increase its demand.

The proliferation of dozens of similar models by researchers since TypeSafe’s debut highlights widespread interest, yet raises questions about their practical value. Brooker suggests the key challenge lies in optimizing the model’s rapid decision-making without compromising its intelligence.

“There is a very careful balance to be found where you want to push its performance on accuracy and calibration on these kinds of tasks, without degrading its performance on understanding different languages, on having the kind of knowledge it has, which is what makes it general purpose and interesting and useful,” he told TechCrunch.

Nevertheless, he does not necessarily expect frontier labs to dominate this niche, especially since the cost to build something meaningful in smaller markets is often just hundreds or thousands of dollars.

Meanwhile, TypeSafe executives are focusing on refining their approach and improving future models.

“I get that people think it’s a gold rush, but they might be underestimating the difficulty of making the models actually smart,” CEO and founder Diogo Almeida told TechCrunch, adding that he does not yet see real competition for his company emerging.

“The current batch seems more like ML people wanting to implement a cool architecture than a team deeply dedicated to making intelligence useful.”