New Relic Inc. is a San Francisco-based technology company that pioneered application performance monitoring (APM) and provides comprehensive observability solutions. Serving leading customers worldwide, including major brands like Ryanair, New Relic helps organizations monitor and optimize their digital systems to deliver better customer experiences. New Relic faced a challenge common to many rapidly growing enterprises. … Read more
Generative AI and agentic applications are reshaping how businesses operate—from customer support bots to research assistants—and teams need to move from prototype to production quickly. Last year, AWS released Amazon Bedrock AgentCore—a development platform for building, deploying, and scaling AI agents in production. AgentCore provides core building blocks like runtime hosting, memory, tool integration, and … Read more
My first attempt at building a travel planning agent looked exactly like most early prototypes: one big model, a few tools, and a long system prompt. It worked fine until the moment real-world complexity showed up. Flights came from a clean API, hotels lived behind a shifting web UI, and the model kept mixing instructions, … Read more
Today, we’re announcing structured outputs on Amazon Bedrock—a capability that fundamentally transforms how you can obtain validated JSON responses from foundation models through constrained decoding for schema compliance. This represents a paradigm shift in AI application development. Instead of validating JSON responses and writing fallback logic for when they fail, you can move straight to … Read more
Training and deploying large AI models requires advanced distributed computing capabilities, but managing these distributed systems shouldn’t be complex for data scientists and machine learning (ML) practitioners. The command line interface (CLI) and software development kit (SDK) for Amazon SageMaker HyperPod with Amazon Elastic Kubernetes Service (Amazon EKS) orchestration simplify how you manage cluster infrastructure and use … Read more
In the post Evaluating generative AI models with Amazon Nova LLM-as-a-Judge on Amazon SageMaker AI, we introduced the Amazon Nova LLM-as-a-judge capability, which is a specialized evaluation model available through Amazon SageMaker AI that you can use to systematically measure the relative performance of generative AI systems. SageMaker AI now offers a rubric-based large language … Read more
This is a guest post co-written with David Meredith and Josh Zacharias from Associa. Associa, North America’s largest community management company, oversees approximately 7.5 million homeowners with 15,000 employees across more than 300 branch offices. The company manages approximately 48 million documents across 26 TB of data, but their existing document management system lacks efficient … Read more
Embedding models power many modern applications—from semantic search and Retrieval-Augmented Generation (RAG) to recommendation systems and content understanding. However, selecting an embedding model requires careful consideration—after you’ve ingested your data, migrating to a different model means re-embedding your entire corpus, rebuilding vector indexes, and validating search quality from scratch. The right embedding model should deliver … Read more
Marketing teams face major challenges creating campaigns in today’s digital environment. They must navigate through complex data analytics and rapidly changing consumer preferences to produce engaging, personalized content across multiple channels while maintaining brand consistency and working within tight deadlines. Using generative AI can streamline and accelerate the creative process while maintaining alignment with business … Read more
This post is cowritten with James Luo from BGL. Data analysis is emerging as a high-impact use case for AI agents. According to Anthropic’s 2026 State of AI Agents Report, 60% of organizations rank data analysis and report generation as their most impactful agentic AI applications. 65% of enterprises cite it as a top priority. … Read more
Many organizations need to manage file uploads across different cloud storage systems while maintaining security and compliance. Although Google Drive provides APIs for integration, organizations often don’t have the technical experts to interact with these APIs directly. Organizations need an intuitive way to handle file uploads using natural language, without requiring specialized knowledge of the … Read more
Building production-ready AI agents requires careful planning and execution across the entire development lifecycle. The difference between a prototype that impresses in a demo and an agent that delivers value in production is achieved through disciplined engineering practices, robust architecture, and continuous improvement. This post explores nine essential best practices for building enterprise AI agents … Read more
Performing research and clinical analytics on vast amounts of clinical data can be difficult. Healthcare data scientists and epidemiologists possess deep domain expertise in patient care, disease patterns, and clinical outcomes, yet they often spend weeks navigating complex data infrastructures, writing boilerplate code, and wrestling with technical barriers before they can answer a single clinical … Read more
This post was cowritten by Rishi Srivastava and Scott Reynolds from Clarus Care. Many healthcare practices today struggle with managing high volumes of patient calls efficiently. From appointment scheduling and prescription refills to billing inquiries and urgent medical concerns, practices face the challenge of providing timely responses while maintaining quality patient care. Traditional phone systems … Read more
Managing ModelOps workflows can be complex and time-consuming. If you’ve struggled with setting up project templates for your data science team, you know that the previous approach using AWS Service Catalog required configuring portfolios, products, and managing complex permissions—adding significant administrative overhead before your team could start building machine learning (ML) pipelines. Amazon SageMaker AI … Read more
Building AI applications with Amazon Bedrock presents throughput challenges impacting the scalability of your applications. Global cross-Region inference in the af-south-1 AWS Region changes that. You can now invoke models from the Cape Town Region while Amazon Bedrock automatically routes requests to Regions with available capacity. Your applications get consistent response times, your users get reliable experiences, … Read more
Enterprises are managing ever-growing volumes of content, ranging from product catalogs and support articles to knowledge bases and technical documentation. Ensuring this information remains accurate, relevant, and aligned with the latest business facts is a formidable challenge. Manual content review processes are often slow, costly, and unable to keep pace with dynamic business needs. According … Read more
This post was co-written with Saurabh Gupta and Todd Colby from Pushpay. Pushpay is a market-leading digital giving and engagement platform designed to help churches and faith-based organizations drive community engagement, manage donations, and strengthen generosity fundraising processes efficiently. Pushpay’s church management system provides church administrators and ministry leaders with insight-driven reporting, donor development dashboards, and automation … Read more
Organizations managing hundreds of contracts annually face significant inefficiencies, with fragmented systems and complex workflows that require teams to spend hours on contract review cycles. This solution addresses these challenges through multi-agent collaboration—specialized AI agents that can work simultaneously on different aspects of contract analysis, reducing cycle times while maintaining accuracy and oversight. This guide … Read more
AWS AppSync Events can help you create more secure, scalable Websocket APIs. In addition to broadcasting real-time events to millions of Websocket subscribers, it supports a crucial user experience requirement of your AI Gateway: low-latency propagation of events from your chosen generative AI models to individual users. In this post, we discuss how to use … Read more
This post is cowritten by Nikhil Mathugar, Marc Breslow and Sudhanshu Sinha from Totogi. This blog post describes how Totogi automates change request processing. Totogi is an AI company focused on helping helping telecom (telco) companies innovate, accelerate growth and adopt AI at scale. BSS Magic, Totogi’s flagship product, connects and models telco business operations, … Read more
Agentic-AI has become essential for deploying production-ready AI applications, yet many developers struggle with the complexity of manually configuring agent infrastructure across multiple environments. Infrastructure as code (IaC) facilitates consistent, secure, and scalable infrastructure that autonomous AI systems require. It minimizes manual configuration errors through automated resource management and declarative templates, reducing deployment time from … Read more
The Amazon.com Catalog is the foundation of every customer’s shopping experience—the definitive source of product information with attributes that power search, recommendations, and discovery. When a seller lists a new product, the catalog system must extract structured attributes—dimensions, materials, compatibility, and technical specifications—while generating content such as titles that match how customers search. A title … Read more
PDI Technologies is a global leader in the convenience retail and petroleum wholesale industries. They help businesses around the globe increase efficiency and profitability by securely connecting their data and operations. With 40 years of experience, PDI Technologies assists customers in all aspects of their business, from understanding consumer behavior to simplifying technology ecosystems across … Read more
CLICKFORCE is one of leaders in digital advertising services in Taiwan, specializing in data-driven advertising and conversion (D4A – Data for Advertising & Action). With a mission to deliver industry-leading, trend-aligned, and innovative marketing solutions, CLICKFORCE helps brands, agencies, and media partners make smarter advertising decisions. However, as the advertising industry rapidly evolves, traditional analysis methods … Read more
This post was co-written with Naveen Pollamreddi and Seth Krause from Thomson Reuters. Thomson Reuters (TR) is a leading AI and technology company dedicated to delivering trusted content and workflow automation solutions. With over 150 years of expertise, TR provides essential solutions across legal, tax, accounting, risk, trade, and media sectors in a fast-evolving world. AI … Read more
Today, most agents operate only on what’s visible in the current interaction: they can access facts and knowledge, but they can’t remember how they solved similar problems before or why certain approaches worked or failed. This creates a significant gap in their ability to learn and improve over time. Amazon Bedrock AgentCore episodic memory addresses … Read more
This post was co-authored with Benjamin Kleppe, Machine Learning Engineering Lead at bunq. The integration of agentic AI is transforming the banking industry, marking a significant shift from traditional customer service systems. Agentic AI demonstrates autonomous decision-making capabilities in complex financial environments, enabling banks to provide round-the-clock multilingual support, process transactions, and deliver personalized financial … Read more
Multi-agent solutions, in which networks of agents collaborate, coordinate, and reason together, are changing how we approach real-world challenges. Enterprises manage environments with multiple data sources, changing goals, and various constraints. This is where multi-agent architectures shine. By empowering multiple agents that each have specialized tools, memory, or perspectives to interact and reason as a … Read more
We are excited to announce the general availability of multimodal retrieval for Amazon Bedrock Knowledge Bases. This new capability adds native support for video and audio content, on top of text and images. With it you can build Retrieval Augmented Generation (RAG) applications that can search and retrieve information across text, images, audio, and video—all … Read more