Official technical community of Amazon Cloud. Shares practical AI/ML, big data, database, modern app development, IoT content, offers comprehensive learning resources, hosts regular developer events, and continuously empowers developers.
Amazon Bedrock introduces three service tiers—Priority, Standard, and Flex—enabling developers to match AI workload requirements with the appropriate performance level and cost, supported by concrete usage examples, a selection framework, and monitoring guidance.
The newly available Amazon EC2 P6‑B300 instance, powered by NVIDIA Blackwell Ultra GPUs, offers up to 2× network bandwidth and 1.5× GPU memory compared with its predecessor, delivering 6.4 Tbps EFA throughput, 2.1 TB GPU memory, and optimized storage options for large‑scale AI training and deployment, especially for MoE and multimodal models.
This article compares Amazon Bedrock AgentCore's container‑based and direct‑code deployment options, walks through a step‑by‑step Python example of the zip‑deployment workflow, and shows how the latter can cut iteration time from 30 seconds to about 10 seconds while simplifying setup.
AgentCore Identity, an Amazon Bedrock service, offers centralized agent identity management, secure token storage, native OAuth 2.0 support, and fine-grained access control, enabling AI agents to authenticate users, retrieve and store credentials safely, and perform actions such as scheduling Google Calendar events through a detailed end-to-end flow.
The article demonstrates how to build a modular, multi‑Agent voice banking assistant using Amazon Nova Sonic as the speech interface and Amazon Bedrock AgentCore to orchestrate specialized sub‑Agents for identity verification, account queries, and mortgage assistance, while discussing design trade‑offs, tool‑call integration, and best‑practice recommendations.
The article compares Vibe Coding, a prompt‑driven approach that lets large models generate prototype code from natural language, with Spec‑Driven Development, which starts from a written specification to guide AI, and illustrates the latter by adding context‑management to the Amazon Q Developer CLI in just two days instead of four weeks.
Amazon Nova Web Grounding is an out‑of‑the‑box RAG tool for Amazon Bedrock that automatically retrieves and cites up‑to‑date information, reduces hallucinations, and lets developers create accurate, real‑time AI applications using simple Python code.
This guide walks through Amazon Bedrock senior architect Prasanna Sridharan's video demo of AgentCore Identity, showing how to centrally manage AI agent identities, tokens, and API keys, integrate with Amazon Cognito and OAuth, use the AgentCore SDK for runtime permissions, and apply scoped access control in real-world scenarios.
Amazon Nova, a new multimodal embedding model now available on Amazon Bedrock, unifies text, document, image, video, and audio into a single semantic space, offering up to 8000‑token context, multiple output dimensions, and detailed Python examples for embedding generation, storage, and cross‑modal search.
This article walks developers through two concrete Agentic AI projects—a Hong Kong weather chatbot built with Amazon Nova Act and a personalized math‑teaching agent using the open‑source Strands Agents framework—each accompanied by full implementation code and live demos.
