Fresh intelligence
Fix evaluation bias to unlock better models on Amazon Bedrock
Property Finder found that 96.8% of their vision-AI evaluation labels were inherited from the incumbent model, hiding its true accuracy. See how they built unbiased ground truth, applied evolutionary prompt optimization, and selected a more
AWS 人工智能 · Published 10/28/2026, 00:53Exowatt beats frontier models on accuracy with SageMaker serverless model customization
In this post, we show how Exowatt used Amazon SageMaker AI serverless model customization to build a repeatable AI pipeline that produces task-specific fine-tuned models for two deployment targets, edge and cloud, achieving higher accuracy
AWS 人工智能 · Published 10/28/2026, 00:50In 2027, start a global business with Amazon and AI
雨果跨境·亚马逊频道 · Published 10/27/2026, 17:52Amazon launches seller workflow AI—AI can already handle these 5 tasks for you
Will operations roles be replaced?
雨果跨境 · Published 10/27/2026, 16:20Fleet-wide computer vision lifecycle at the edge with SageMaker SDK v3
Fleet-wide computer vision needs a model per camera, not one model for the whole fleet. This post presents a working Amazon SageMaker SDK v3 reference architecture that trains, quality-gates, compiles per-camera models with SageMaker Neo, a
AWS 人工智能 · Published 10/27/2026, 01:56Groundhog Day for AI agents: Prompt caching patterns for using OpenAI models on Amazon Bedrock
Every time an agent takes a step, it re-reads its entire context before acting. Here is how prompt caching for OpenAI models on Amazon Bedrock lets your agent remember, cutting input cost and latency without resending the same tools, instru
AWS 人工智能 · Published 10/27/2026, 01:27Build agentic retrieval on a Managed Amazon Bedrock Knowledge Base with CDK
Build enterprise agentic retrieval on a Managed Amazon Bedrock Knowledge Base with the AWS CDK: an agent that routes across two knowledge bases, retrieves through the AgentCore Gateway, and returns grounded, cited answers, with seven layers
AWS 人工智能 · Published 10/27/2026, 01:15Multi-Turn Reinforcement Learning on Amazon SageMaker AI: A hands-on guide
Multi-Turn Reinforcement Learning (MTRL) on Amazon SageMaker AI trains models on the outcome of a whole multi-step task rather than labeled steps. This hands-on guide walks the full pipeline using Wordle: deploying the agent and reward on A
AWS 人工智能 · Published 10/24/2026, 01:48Visualize points and routes with GeoJSON in Amazon Quick Sight layer maps
Amazon Quick Sight layer maps now support Point and LineString geometry from the same GeoJSON workflow, so you can plot store locations and the routes between them. This post covers the dataset and GeoJSON structure layer maps require, when
AWS 人工智能 · Published 10/24/2026, 00:24How Bayer Crop Science built an agentic decision engine on Amazon Bedrock AgentCore with AWS Unified Operations
Bayer Crop Science built the Agentic Decision Engine (ADE), a multi-agent platform on Amazon Bedrock AgentCore that lets breeders, analysts, and researchers ask natural language questions about their analytics platform. This post covers the
AWS 人工智能 · Published 10/24/2026, 00:21