AWSML

The adoption and implementation of generative AI inference has increased with organizations building more operational workloads that use AI capabilities in production at scale. To help customers achieve the scale of their generative AI applications, Amazon Bedrock offers cross-Region inference (CRIS) profiles. CRIS is a powerful feature that organizations can use to seamlessly distribute inference … Read more

As your conversational AI initiatives evolve, developing Amazon Lex assistants becomes increasingly complex. Multiple developers working on the same shared Lex instance leads to configuration conflicts, overwritten changes, and slower iteration cycles. Scaling Amazon Lex development requires isolated environments, version control, and automated deployment pipelines. By adopting well-structured continuous integration and continuous delivery (CI/CD) practices, … Read more

Organizations increasingly deploy custom large language models (LLMs) on Amazon SageMaker AI real-time endpoints using their preferred serving frameworks—such as SGLang, vLLM, or TorchServe—to help gain greater control over their deployments, optimize costs, and align with compliance requirements. However, this flexibility introduces a critical technical challenge: response format incompatibility with Strands agents. While these custom … Read more

Organizations can face two critical challenges with conversational AI. First, users need answers where they work—in their CRM, support console, or analytics portal—not in separate tools. Second, implementing a secure embedded chat in their applications can require weeks of development to build authentication, token validation, domain security, and global distribution infrastructure. Amazon Quick Suite embedded … Read more

Call center analytics play a crucial role in improving customer experience and operational efficiency. With foundation models (FMs), you can improve the quality and efficiency of call center operations and analytics. Organizations can use generative AI to assist human customer support agents and managers of contact center teams, so they can gain insights that are … Read more

This post is cowritten by Jeremy Jacobson and Rado Fulek from Ricoh. This post demonstrates how enterprises can overcome document processing scaling limits by combining generative AI, serverless architecture, and standardized frameworks. Ricoh engineered a repeatable, reusable framework using the AWS GenAI Intelligent Document Processing (IDP) Accelerator. This framework reduced customer onboarding time from weeks … Read more

In this first post in a two-part series, we examine how retailers can implement a virtual try-on to improve customer experience. In part 2, we will further explore real-world applications and benefits of this innovative technology. Every fourth piece of clothing bought online is returned to the retailer, feeding into America’s $890 billion returns problem … Read more

This post was co-written with Davesh Maheshwari from Lendi Group and Samuel Casey from Mantel Group. Most Australians don’t know whether their home loan is still competitive. Rates shift, property values move, personal circumstances change—yet for the average homeowner, staying informed of these changes is difficult. It’s often their largest financial commitment, but it’s also … Read more

Organizations face challenges in quickly detecting and responding to user account security events, such as repeated login attempts from unusual locations. Although security data exists across multiple applications, manually correlating information and making corrective actions often delays effective response. With Amazon Quick Suite and Tines, you can automate the investigation and remediation process by integrating … Read more

Large language models (LLMs) perform well on general tasks but struggle with specialized work that requires understanding proprietary data, internal processes, and industry-specific terminology. Supervised fine-tuning (SFT) adapts LLMs to these organizational contexts. SFT can be implemented through two distinct methodologies: Parameter-Efficient Fine-Tuning (PEFT), which updates only a subset of model parameters, offering faster training … Read more

Customer service teams face a persistent challenge. Existing chat-based assistants frustrate users with rigid responses, while direct large language model (LLM) implementations lack the structure needed for reliable business operations. When customers need help with order inquiries, cancellations, or status updates, traditional approaches either fail to understand natural language or can’t maintain context across multistep … Read more

Are you struggling to balance generative AI safety with accuracy, performance, and costs? Many organizations face this challenge when deploying generative AI applications to production. A guardrail that’s too strict blocks legitimate user requests, which frustrates customers. One that’s too lenient exposes your application to harmful content, prompt attacks, or unintended data exposure. Finding the … Read more

There’s a lot of excitement right now about AI enabling mainframe application modernization. Boards are paying attention. CIOs are getting asked for a plan. AI is a genuine accelerator for COBOL modernization but to get results, AI needs additional context that source code alone can’t provide.Here’s what we’ve learned working with 400+ enterprise customers: mainframe … Read more

Foundation models deliver impressive out-of-the-box performance for general tasks, but many organizations need models to consume their business knowledge. Model customization helps you bridge the gap between general-purpose AI and your specific business needs when building applications that require domain-specific expertise, enforcing communication styles, optimizing for specialized tasks like code generation, financial reasoning, or ensuring … Read more

Modern large language model (LLM) deployments face an escalating cost and performance challenge driven by token count growth. Token count, which is directly related to word count, image size, and other input factors, determines both computational requirements and costs. Longer contexts translate to higher expenses per inference request. This challenge has intensified as frontier models … Read more

Organizations and individuals running multiple custom AI models, especially recent Mixture of Experts (MoE) model families, can face the challenge of paying for idle GPU capacity when the individual models don’t receive enough traffic to saturate a dedicated compute endpoint. To solve this problem, we have partnered with the vLLM community and developed an efficient … Read more

Large conferences and events generate overwhelming amounts of information—from hundreds of sessions and workshops to speaker profiles, venue maps, and constantly updating schedules. While basic AI assistants can answer simple questions about event logistics, most fail to deliver the personalized guidance and contextual awareness that attendees need to navigate complex, multi-day conferences effectively. More importantly, … Read more

Critical labor shortages are constraining growth across manufacturing, logistics, construction, and agriculture. The problem is particularly acute in construction: nearly 500,000 positions remain unfilled in the United States, with 40% of the current workforce approaching retirement within the decade. These workforce limitations result in delayed projects, escalating costs, and deferred development plans. To address these … Read more

In precision medicine, researchers developing diagnostic tests for early disease detection face a critical challenge: datasets containing thousands of potential biomarkers but only hundreds of patient samples. This curse of dimensionality can determine the success or failure of breakthrough discoveries. Modern bioinformatics use multiple omic modalities—genomics, lipidomics, proteomics, and metabolomics—to develop early disease detection tests. … Read more

This blog post was co-authored with Johannes Maunz, Tobias Bösch Borgards, Aleksander Cisłak, and Bartłomiej Gralewicz from Hexagon. Hexagon is the global leader in measurement technologies and provides the confidence that vital industries rely on to build, navigate, and innovate. From microns to Mars, Hexagon’s solutions drive productivity, quality, safety, and sustainability across aerospace, agriculture, … Read more

This post is cowritten by Jeff Boudier, Simon Pagezy, and Florent Gbelidji from Hugging Face. Agentic AI systems represent an evolution from conversational AI to autonomous agents capable of complex reasoning, tool usage, and code execution. Enterprise applications benefit from strategic deployment approaches tailored to specific needs. These needs include managed endpoints, which deliver auto-scaling capabilities, foundation … Read more

In 2025, Amazon SageMaker AI saw dramatic improvements to core infrastructure offerings along four dimensions: capacity, price performance, observability, and usability. In this series of posts, we discuss these various improvements and their benefits. In Part 1, we discuss capacity improvements with the launch of Flexible Training Plans. We also describe improvements to price performance … Read more

In 2025, Amazon SageMaker AI made several improvements designed to help you train, tune, and host generative AI workloads. In Part 1 of this series, we discussed Flexible Training Plans and price performance improvements made to inference components. In this post, we discuss enhancements made to observability, model customization, and model hosting. These improvements facilitate … Read more

Amazon Quick supports Model Context Protocol (MCP) integrations for action execution, data access, and AI agent integration. You can expose your application’s capabilities as MCP tools by hosting your own MCP server and configuring an MCP integration in Amazon Quick. Amazon Quick acts as an MCP client and connects to your MCP server endpoint to access … Read more