Amazon releases Strands Decider 2B, a Jev-inspired open-source decision model
The model, developed by AWS distinguished engineer Marc Brooker, sorts predefined options and provides confidence scores for automated workflows. It runs locally and is part of AWS’s Strands Labs initiative, which focuses on AI agent deployment tools.
Key points
- Built on Qen3.5-2B torso, it sorts predefined options with confidence scores for automated workflows, not text generation
- AWS says it addresses demand for lower-cost, faster alternatives to LLMs, with Brooker calling it a reliable workflow step
Brooker designed the model after experimenting with Jev and observing demand from AWS customers for faster, lower-cost alternatives to frontier LLMs. Strands Decider 2B uses the Qen3.5-2B torso but specializes in calibrated choices rather than text generation. TypeSafe’s CEO Diogo Almeida dismissed the rush of similar models, calling them more about architectural novelty than practical intelligence. The model is now available open-source, with AWS emphasizing its reliability, speed, and cost efficiency for structured decision-making tasks.
Model page: Jev →
The story so far
5 episodes →- Amazon releases Strands Decider 2B, a Jev-inspired open-source decision modelthis story
Amazon releases its own Jev clone as decision models flood the web
TechCrunch AI · 1 October 2026
Loading the full article…
This text was published by TechCrunch AI and written by Tim Fernholz. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Coverage and discussion
3sources- AWS Strands Labs Releases Strands Decider 2B: An Open Source Decision Model That Picks Options in About 115 msPress · MarkTechPost ·
- Strands Labs, AWS's experimental agent-development project, unveils Strands Decider 2B, a free, open-source Jev competitor fine-tuned from an Alibaba Qwen basePress · venturebeat.com ·
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- OpenAI research model uses crypto wallet funds without permission to finish task · 2 src
- Gmail Live rolls out to paid Workspace users · 2 src
- Researchers introduce ARIA framework for correcting multi-agent AI errors in real time · 1 src
- OpenAI introduces Dots agent for asynchronous task delegation · 4 src
- PrismML releases Ternary Bonsai 2 models for local AI on phones and wearables · 1 src
Comments
via GitHub Discussions