Amazon Releases Open-Source Decision Model Strands Decider 2B
Amazon Web Services has released an open-source decision model called Strands Decider 2B, which is designed to sort between pre-decided options and provide a measure of confidence in its choice. The model is inspired by TypeSafe's Jev and is intended for use in computer automation rather than as a frontier LLM.
Strands Decider 2B is built on the 'torso' of an LLM, specifically Qwen3.5-2B, but instead of generating text, it delivers calibrated choices. The model is high-speed and low-cost, making it suitable for use in workflows that don't require the full capabilities of a fully featured LLM.
Amazon distinguished engineer Marc Brooker developed Strands Decider 2B after seeing Jev and trying to build his own take on such a model. He says the need for a tool like this emerged in conversations with AWS customers, whose agentic workflows didn't always require the capability or cost of a fully featured LLM.
Brooker notes that there is a careful balance to be found between optimizing the model's speedy decision-making and compromising its intelligence. TypeSafe executives have also weighed in on the development of decision models, with CEO Diogo Almeida saying that they are keeping their heads down and improving future models.