University of California Los Angeles delivers an immersive theater experience with AWS generative AI services In this post, we will walk through the performance constraints and design choices by OARC and REMAP teams at UCLA, including how AWS serverless infrastructure, AWS Managed Services, and generative AI services supported the rapid design and deployment of our solution. We will also describe our use of Amazon SageMaker AI and how it can be used reliably in immersive live experiences.
https://aws.amazon.com/blogs/m....achine-learning/univ

Building AI-Powered Voice Applications: Amazon Nova Sonic Telephony Integration Guide Available through the Amazon Bedrock bidirectional streaming API, Amazon Nova Sonic can connect to your business data and external tools and can be integrated directly with telephony systems. This post will introduce sample implementations for the most common telephony scenarios.
https://aws.amazon.com/blogs/m....achine-learning/buil

How Condé Nast accelerated contract processing and rights analysis with Amazon Bedrock In this post, we explore how Condé Nast used Amazon Bedrock and Anthropic’s Claude to accelerate their contract processing and rights analysis workstreams. The company’s extensive portfolio, spanning multiple brands and geographies, required managing an increasingly complex web of contracts, rights, and licensing agreements.
https://aws.amazon.com/blogs/m....achine-learning/how-

Apply fine-grained access control with Bedrock AgentCore Gateway interceptors We are launching a new feature: gateway interceptors for Amazon Bedrock AgentCore Gateway. This powerful new capability provides fine-grained security, dynamic access control, and flexible schema management.
https://aws.amazon.com/blogs/m....achine-learning/appl

Managed Tiered KV Cache and Intelligent Routing for Amazon SageMaker HyperPod In this post, we introduce Managed Tiered KV Cache and Intelligent Routing for Amazon SageMaker HyperPod, new capabilities that can reduce time to first token by up to 40% and lower compute costs by up to 25% for long context prompts and multi-turn conversations. These features automatically manage distributed KV caching infrastructure and intelligent request routing, making it easier to deploy production-scale LLM inference workloads with enterprise-grade performance while significantly reducing operational overhead.
https://aws.amazon.com/blogs/m....achine-learning/mana