Reactive Machines

Batch write and discover records in Amazon SageMaker Feature Store

Batch write and discover records in Amazon SageMaker Feature Store

[ad_1] Amazon SageMaker Feature Store is a fully managed, purpose-built repository to store, share, and manage features for machine learning…
How Decathlon runs demand forecasting at scale with Chronos-2

How Decathlon runs demand forecasting at scale with Chronos-2

[ad_1] This post is co-written with Vianney Bruned, Filippo Giruzzi, Belkiss Saidi, and Carlos Ramirez from Decathlon. Decathlon is one…
Agent Seer: Synthesizing Scenarios from Specification Understanding

Agent Seer: Synthesizing Scenarios from Specification Understanding

[ad_1] Evaluating AI agents that use external tools requires realistic test scenarios that capture how practitioners compose tools and iterate…
Build agentic creative workflows with Amazon Quick and fal

Build agentic creative workflows with Amazon Quick and fal

[ad_1] Creative teams face growing demand for more assets, formats, and revisions, while their scripts, references, models, and outputs often…
Introducing India cross-Region inference for OpenAI GPT-5.6 models on Amazon Bedrock

Introducing India cross-Region inference for OpenAI GPT-5.6 models on Amazon Bedrock

[ad_1] Amazon Bedrock now supports the OpenAI GPT-5.6 models, Terra and Luna, in India, with India geographic cross-Region inference. If…
Introducing OpenAI models on Amazon Bedrock for in-country inferencing in India

Introducing OpenAI models on Amazon Bedrock for in-country inferencing in India

[ad_1] Amazon Bedrock now supports the OpenAI GPT-5.6 models, Terra and Luna, in India, with India geographic cross-Region inference. If…
Deepgram deepens Amazon SageMaker AI observability with Enhanced Metrics

Deepgram deepens Amazon SageMaker AI observability with Enhanced Metrics

[ad_1] Self-hosted speech AI has historically carried an observability trade-off. The service can tell you an endpoint is up and…
From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers

From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers

[ad_1] Designing effective reward signals for open-domain question answering is challenging because high-quality responses must simultaneously satisfy multiple aspects of…
Evaluate any agent framework with Amazon Bedrock AgentCore Evaluations

Evaluate any agent framework with Amazon Bedrock AgentCore Evaluations

[ad_1] AI teams building production agents face a frustrating asymmetry: the diversity of agent frameworks keeps growing, but evaluation tooling…
Back to top button

Enjoy this blog? Please spread the word :)