Amazon releases its own Jev clone as decision models flood the web
techcrunch ·
Amazon Web Services has released Strands Decider 2B, an open-source decision model inspired by TypeSafe’s Jev, designed to offer high-speed and low-cost automation for AI workflows. Unlike traditional large language models that generate text, this model is built on a Qwen3.5-2B backbone but outputs calibrated choices with confidence scores to help agents determine their next steps reliably. AWS distinguished engineer Marc Brooker developed the project after observing customer needs for tools that are more efficient than full-featured LLMs for specific workflow decisions. The release coincides with similar announcements from competitors like OpenAI, highlighting a growing trend of specialized decision models flooding the market. While TypeSafe CEO Diogo Almeida suggests that creating truly smart decision models remains difficult and underestimates by some newcomers, Amazon aims to provide a robust solution for agentic deployment. These models seek to balance speed and accuracy without compromising the underlying intelligence required for general-purpose tasks.
techcrunch