Today, we’re excited to announce the Amazon Bedrock AgentCore Model Context Protocol (MCP) Server. With built-in support for runtime, gateway integration, identity management, and agent memory, the AgentCore MCP Server is purpose-built to speed up creation of components compatible with Bedrock AgentCore. You can use the AgentCore MCP server forContinue Reading
In the benefits administration industry, claims processing is a vital operational pillar that makes sure employees and beneficiaries receive timely benefits, such as health, dental, or disability payments, while controlling costs and adhering to regulations like HIPAA and ERISA. Businesses aim to optimize the workflow—covering claim submission, validation, adjudication, payment,Continue Reading
As organizations scale their AI infrastructure to support trillion-parameter models, they face a difficult trade-off: reduced training time with lower cost or faster training time with a higher cost. When they checkpoint frequently to speed up recovery time and minimize lost training time, they incur in substantially higher storage cost.Continue Reading
Every day, organizations process millions of documents, including invoices, contracts, insurance claims, medical records, and financial statements. Despite the critical role these documents play, an estimated 80–90% of the data they contain is unstructured and largely untapped, hiding valuable insights that could transform business outcomes. Despite advances in technology, manyContinue Reading
As an Amazon Web Services (AWS) enterprise customer, you’re probably exploring ways to use generative AI to enhance your business processes, improve customer experiences, and drive innovation. With a variety of options available—from Amazon Q Business to other AWS services or third-party offerings—choosing the right tool for your use caseContinue Reading
This post is co-written with Kshitiz Gupta, Wenhan Tan, Arun Raman, Jiahong Liu, and Eiluth Triana Isaza from NVIDIA. As large language models (LLMs) and generative AI applications become increasingly prevalent, the demand for efficient, scalable, and low-latency inference solutions has grown. Traditional inference systems often struggle to meet theseContinue Reading
Today, we’re excited to announce that Amazon SageMaker HyperPod now supports deploying foundation models (FMs) from Amazon SageMaker JumpStart, as well as custom or fine-tuned models from Amazon S3 or Amazon FSx. With this launch, you can train, fine-tune, and deploy models on the same HyperPod compute resources, maximizing resourceContinue Reading
Amazon SageMaker HyperPod now provides a comprehensive, out-of-the-box dashboard that delivers insights into foundation model (FM) development tasks and cluster resources. This unified observability solution automatically publishes key metrics to Amazon Managed Service for Prometheus and visualizes them in Amazon Managed Grafana dashboards, optimized specifically for FM development with deepContinue Reading
Today, we’re excited to announce a significant improvement to the developer experience of Amazon Bedrock: API keys. API keys provide quick access to the Amazon Bedrock APIs, streamlining the authentication process so that developers can focus on building rather than configuration. CamelAI is an open-source, modular framework for building intelligentContinue Reading
Modern generative AI model providers require unprecedented computational scale, with pre-training often involving thousands of accelerators running continuously for days, and sometimes months. Foundation Models (FMs) demand distributed training clusters — coordinated groups of accelerated compute instances, using frameworks like PyTorch — to parallelize workloads across hundreds of accelerators (likeContinue Reading
