Amazon releases its own Jev clone as decision models flood the web
- ID
- 30848
- Status
- summarized
- Published
- 02 Oct 2026, 12:49 AM
- Fetched
- 02 Oct 2026, 1:32 AM
- Provider
- TechCrunch
- Category
- technology
- Original URL
- https://techcrunch.com/2026/10/01/amazon-releases-its-own-jev-clone-as-decision-models-flood-the-web/
- Source URL
- https://techcrunch.com/feed/
Summary
- Score
- 7.0
- Created
- 02 Oct 2026, 1:32 AM
- Tags
- Audience
- developersai_agent_usersai_ml_learnerssaas_founders
What happened
AWS released Strands Decider 2B, an open-source 'decision model' inspired by TypeSafe's Jev, the same week OpenAI announced a comparable offering. Built on the torso of Qen3.5-2B, it doesn't generate text — it picks between pre-decided options and returns a calibrated confidence score, and it's small enough to run locally. Amazon distinguished engineer Marc Brooker built an early version after seeing Jev; it briefly topped the Jevbench ranking for models of its size before AWS cleaned it up and shipped it via Strands Labs.
Why it matters
If your agent workflow uses a full LLM call just to answer 'what do I do next?', a 2B local decider with confidence scores can replace that step with lower latency and no per-call API bill — and because the answer domain is closed, you can gate actions on the confidence value instead of parsing free text. Worth benchmarking on your own routing steps before assuming it beats your current prompt.
Discussion angle
Which steps in your agent loop are actually decisions (closed set of options) versus generation? Try swapping one of those for Strands Decider 2B locally and compare latency, cost, and whether the confidence score is trustworthy enough to auto-approve an action.