We listed memory as a use case when we launched strands-decider. I went and built it: a decision model gating long term memory retrieval in a Strands agent. Eight memory calls became three and 147 injected records became 25, with the answers unchanged. The wording of the question mattered more than anything else.
Strands Decider 2B is a small, open source decision model built for fast experimentation, local development, and innovation. A 2B model that picks between options and scores them in tens of milliseconds, with calibrated confidence.
Gating an agent tool call before it runs, using Jev as the semantic classifier and the Strands Interventions API as the control point. Jev answers a narrow typed question, ordinary Python makes the decision.
I joined the AWS Developers Podcast to dig into Jev, TypeSafe AI's new System One decision model, what it actually is, and why it points to a shift away from reaching for one giant LLM for everything.
The question I was asked, taken seriously. Four experiments later: under the only definition we can test, machine originality is already real, provable in a 111k-parameter model. What's missing is expression, not ability. Here's why.
AI agents deploying infrastructure directly into your AWS account is ClickOps at machine speed. The Agent Toolkit for AWS shows how to keep agents producing IaC instead.
Let LLMs write Python that orchestrates parallel tool calls in a single invocation — Pydantic Monty is the sandboxed interpreter that makes it safe and fast.
I tested 27 models on Amazon Bedrock for em dash usage. Llama produces zero. Claude and Palmyra can't stop. What does that tell us about how LLMs learn style?
My AI agent has access to my email and Slack. Here are four tactics I use to stop it from sending a career-ending message — from system prompts to deterministic hooks, LLM-as-a-judge steering, and Cedar policies at cloud scale.
How to wire together AgentCore Browser, Nova Act, and IAM authentication to build a production browser agent on AWS, with complete working code.