Tag: Announcement
16 posts
Evaluating structured agent output, field by field, with Strands Evals
StructuredOutputSimilarity scores structured agent output field by field with Stickler: deterministic, per-field accuracy with no LLM judge in the default path.
Strands Decider adds four Gemma 4 models
Four new Strands Decider models built on Gemma 4 let developers compare sizes for routing, guardrails, evaluation, and other agent decisions.
Strands Box: The Big Picture
Strands Box, now in developer preview, is an open source local sandbox for AI agents that pairs operating-system isolation with Dogwood semantic policy. Here's why semantic policy matters, and how Box's design follows from it.
Bidi Agents now GA
The easiest way to create voice agents with direct support for Amazon Nova Sonic, OpenAI, and Gemini models.
Introducing Strands Decider 2B: a small, open source, decision model
Strands Decider 2B is a small, open source, decision model optimized for fast experimentation, local development, and innovation.
Introducing Strands harness: frontier performance with 28% lower token cost
Strands harness is a fully assembled, customizable, state-of-the-art agent you run locally or deploy anywhere.
Strands Team AI Usage Reflection
A reflection on the impact that AI has had on the strands agents team, our thoughts about it, and how we intend to address the issues we are facing.
Our production SDK hit 99.95% on ARC-AGI-3
Strands Agents scored 99.95% on ARC-AGI-3 using the same minimal harness that developers ship to production every day
Reduced cost, better isolation, and more resilience: Strands Agents evolves next-gen capabilities
Strands Agents ships context management that cuts costs in half, Strands Shell for sandboxed agent execution, and chaos testing and red teaming in Strands Evals 1.0.
Multimodal evaluators: MLLM-as-a-judge for image-to-text tasks in Strands Evals
Announcing four new MLLM-as-a-Judge evaluators for image-to-text tasks in Strands Evals: Overall Quality, Correctness, Faithfulness, and Instruction Following — automated, image-grounded scoring with reasoning.
What We Learned from One Year of Building Production Agents
Strands Agents turned one year old. Here are the key lessons our engineers learned after open sourcing this framework and hitting 25 million downloads.
Introducing Strands Agents TypeScript 1.0: Build Production Agents in TypeScript
Version 1.0 of the Strands Agents TypeScript SDK is here. Build type-safe AI agents with full model provider support, custom tools, plugins, and multi-agent orchestration in Node.js and the browser.
The Strands Agents Community Has a New Home
The Strands Agents Discord server is live. A place for builders to get real-time help, share what they've built, and connect with the Strands team.
Strands Agents TypeScript SDK: Build AI Agents in TypeScript
The Strands Agents TypeScript SDK brings the model-driven approach to the TypeScript ecosystem. Build type-safe AI agents that run in Node.js and the browser.
Introducing Strands Labs: Get hands-on today with state-of-the-art, experimental approaches to agentic development
Strands Labs is a new GitHub organization designed to give developers the ability to get hands-on with experimental, state-of-the-art approaches to agentic AI development.
Introducing Strands Agents, an Open Source AI Agents SDK
Strands Agents is an open source SDK that takes a model-driven approach to building and running AI agents in just a few lines of code.