{"version":1,"type":"story","url":"https://digestai.news/story/amazon-releases-strands-decider-2b-a-jev-inspired-open-source-decision","json":"https://digestai.news/story/amazon-releases-strands-decider-2b-a-jev-inspired-open-source-decision.json","markdown":"https://digestai.news/story/amazon-releases-strands-decider-2b-a-jev-inspired-open-source-decision.md","slug":"amazon-releases-strands-decider-2b-a-jev-inspired-open-source-decision","headline":"Amazon releases Strands Decider 2B, a Jev-inspired open-source decision model","summary":"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.\n\nBrooker 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.","keyPoints":["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"],"whyItMatters":"Strands Decider 2B fills a niche for automated decision-making in agent workflows, offering speed and cost savings over LLMs. Its open-source release could accelerate adoption of specialized models beyond frontier AI.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Amazon Web Services","TypeSafe","AWS","Strands Labs"],"models":["Strands Decider 2B","Jev","Qen3.5-2B"],"people":["Marc Brooker","Diogo Almeida"]},"firstPublishedAt":"2026-10-01T16:49:22Z","updatedAt":"2026-10-01T18:15:02Z","sourceCount":2,"hasPrimarySource":false,"sources":[{"outlet":"TechCrunch AI","title":"Amazon releases its own Jev clone as decision models flood the web","url":"https://techcrunch.com/2026/10/01/amazon-releases-its-own-jev-clone-as-decision-models-flood-the-web","publishedAt":"2026-10-01T16:49:22Z","type":"press","primary":false,"lead":true},{"outlet":"venturebeat.com","title":"Strands Labs, AWS's experimental agent-development project, unveils Strands Decider 2B, a free, open-source Jev competitor fine-tuned from an Alibaba Qwen base","url":"https://venturebeat.com/technology/amazon-unveils-a-free-fast-open-source-jev-killer-strands-decider-2b-makes-decisions-in-fractions-of-a-second","publishedAt":"2026-10-01T18:15:02Z","type":"press","primary":false,"lead":false}],"sourceNotes":null,"discussions":[],"thread":{"title":"TypeSafe Jev Launch and Amazon Response","url":"https://digestai.news/thread/typesafe-in-talks-to-raise-1b-at-10b-valuation","storyCount":4},"cite":{"text":"Digest AI, \"Amazon releases Strands Decider 2B, a Jev-inspired open-source decision model\", 1 October 2026, https://digestai.news/story/amazon-releases-strands-decider-2b-a-jev-inspired-open-source-decision","publisher":"Digest AI","title":"Amazon releases Strands Decider 2B, a Jev-inspired open-source decision model","datePublished":"2026-10-01T16:49:22Z","url":"https://digestai.news/story/amazon-releases-strands-decider-2b-a-jev-inspired-open-source-decision"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}