Amazon releases compact model that ranks options with confidence scores
Amazon has released Strands Decider 2B, an open-source decision model inspired by TypeSafe's Jev model. This reflects a growing trend of AI developers creating smaller, specialised models designed for automation tasks rather than general-purpose language generation. The model offers a faster, more cost-effective alternative to large language models for workflows that only need to choose between predetermined options.
Amazon's model is built on Qwen3.5-2B but, unlike traditional LLMs, outputs calibrated decisions with confidence scores rather than generated text. Created by Amazon distinguished engineer Marc Brooker, the model briefly topped the Jevbench ranking for its size class. The release coincided with OpenAI announcing a similar offering, and dozens of researchers have developed comparable decision models since TypeSafe introduced the concept, though TypeSafe's CEO argues that true competition has yet to emerge.
- Amazon releases Strands Decider, a specialised AI model for quick, low-cost workflow decisions.
- Decision models are cheaper and faster than full LLMs for specific tasks.
- Dozens of similar models now exist, but founders question their actual effectiveness.
New here? Start with this
Amazon has launched a new artificial intelligence model called Strands Decider 2B, which makes decisions by choosing from predetermined options and assigning confidence scores to each choice. Unlike traditional language models, this tool is built specifically for automating routine business decisions, such as choosing the right customer service response.
The release reflects a broader shift in artificial intelligence development away from massive general-purpose models towards smaller, specialist tools tailored to specific jobs. TypeSafe introduced this concept originally, and since then dozens of researchers, including teams at OpenAI, have developed similar decision-making models for automation tasks.
Specialist models designed for specific tasks appeal to businesses with routine workflows that don't need the full capabilities of large language models. This approach promises faster and more cost-effective automation compared to using general-purpose AI systems.
Read the full article at the source →
Originally published by TechCrunch as “Amazon releases its own Jev clone as decision models flood the web”.