Category: Technical How-to

In this post, we demonstrate that fine-tuning VLMs provides a powerful and flexible approach to automate and significantly enhance document understanding capabilities. We also demonstrate that using focused fine-tuning allows smaller, multi-modal models to compete effectively with much larger counterparts (98% accuracy with Qwen2.5 VL 3B).

In this post, we show you how Amazon Search optimized GPU instance utilization by leveraging AWS Batch for SageMaker Training jobs. This managed solution enabled us to orchestrate machine learning (ML) training workloads on GPU-accelerated instance families like P5, P4, and others. We will also provide a step-by-step walkthrough of the use case implementation.

Enterprises in regulated industries often need mathematical certainty that every AI response complies with established policies and domain knowledge. Regulated industries can’t use traditional quality assurance methods that test only a statistical sample of AI outputs and make probabilistic assertions about compliance. When we launched Automated Reasoning checks in Amazon Bedrock Guardrails in preview at […]

In this post, we explore how to deploy NVIDIA’s Parakeet ASR model on Amazon SageMaker AI using asynchronous inference endpoints to create a scalable, cost-effective pipeline for processing large volumes of audio data. The solution combines state-of-the-art speech recognition capabilities with AWS managed services like Lambda, S3, and Bedrock to automatically transcribe audio files and generate intelligent summaries, enabling organizations to unlock valuable insights from customer calls, meeting recordings, and other audio content at scale .

In this post, we explore advanced cost monitoring strategies for Amazon Bedrock deployments, introducing granular custom tagging approaches for precise cost allocation and comprehensive reporting mechanisms that build upon the proactive cost management foundation established in Part 1. The solution demonstrates how to implement invocation-level tagging, application inference profiles, and integration with AWS Cost Explorer to create a complete 360-degree view of generative AI usage and expenses.

In this post, we introduce a comprehensive solution for proactively managing Amazon Bedrock inference costs through a cost sentry mechanism designed to establish and enforce token usage limits, providing organizations with a robust framework for controlling generative AI expenses. The solution uses serverless workflows and native Amazon Bedrock integration to deliver a predictable, cost-effective approach that aligns with organizational financial constraints while preventing runaway costs through leading indicators and real-time budget enforcement.

In this post, we demonstrate how Amazon Nova Premier with Amazon Bedrock can systematically migrate legacy C code to modern Java/Spring applications using an intelligent agentic workflow that breaks down complex conversions into specialized agent roles. The solution reduces migration time and costs while improving code quality through automated validation, security assessment, and iterative refinement processes that handle even large codebases exceeding token limitations.

In this post, we walk through how to take an ML model built in SageMaker Canvas and deploy it using SageMaker Serverless Inference, helping you go from model creation to production-ready predictions quickly and efficiently without managing any infrastructure. This solution demonstrates a complete workflow from adding your trained model to the SageMaker Model Registry through creating serverless endpoint configurations and deploying endpoints that automatically scale based on demand .

In this post, we explore how Amazon Nova Sonic’s speech-to-speech capabilities can be combined with Amazon Bedrock AgentCore to create sophisticated multi-agent voice assistants that break complex tasks into specialized, manageable components. The approach demonstrates how to build modular, scalable voice applications using a banking assistant example with dedicated sub-agents for authentication, banking inquiries, and mortgage services, offering a more maintainable alternative to monolithic voice assistant designs.

In this post, we demonstrate how to deploy and manage machine learning training workloads using the Amazon SageMaker HyperPod training operator, which enhances training resilience for Kubernetes workloads through pinpoint recovery and customizable monitoring capabilities. The Amazon SageMaker HyperPod training operator helps accelerate generative AI model development by efficiently managing distributed training across large GPU clusters, offering benefits like centralized training process monitoring, granular process recovery, and hanging job detection that can reduce recovery times from tens of minutes to seconds.