AWSML

In high-volume healthcare contact centers, every patient conversation carries both clinical and operational significance, making accurate real-time transcription necessary for automated workflows. Accurate, instant transcription enables intelligent automation without sacrificing clarity or care, so that teams can automate electronic medical record (EMR) record matching, streamline workflows, and eliminate manual data entry. By removing routine process … Read more

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 … Read more

In 2024, we launched the Custom Model Program within the AWS Generative AI Innovation Center to provide comprehensive support throughout every stage of model customization and optimization. Over the past two years, this program has delivered exceptional results by partnering with global enterprises and startups across diverse industries—including legal, financial services, healthcare and life sciences, … Read more

This post was co-written with Kim Nguyen and Shyam Banuprakash from Clario. Clario is a leading provider of endpoint data solutions for systematic collection, management, and analysis of specific, predefined outcomes (endpoints) to evaluate a treatment’s safety and effectiveness in the clinical trials industry, generating high-quality clinical evidence for life sciences companies seeking to bring … Read more

こんにちは, G’day. The recent launch of Anthropic’s Claude Sonnet 4.5 and Claude Haiku 4.5, now available on Amazon Bedrock, marks a significant leap forward in generative AI models. These state-of-the-art models excel at complex agentic tasks, coding, and enterprise workloads, offering enhanced capabilities to developers. Along with the new models, we are thrilled to announce that … Read more

AI agents need to browse the web on your behalf. When your agent visits a website to gather information, complete a form, or verify data, it encounters the same defenses designed to stop unwanted bots: CAPTCHAs, rate limits, and outright blocks. Today, we are excited to share that AWS has a solution. Amazon Bedrock AgentCore … Read more

This post was written with NVIDIA and the authors would like to thank Adi Margolin, Eliuth Triana, and Maryam Motamedi for their collaboration. Organizations today face the challenge of processing large volumes of audio data–from customer calls and meeting recordings to podcasts and voice messages–to unlock valuable insights. Automatic Speech Recognition (ASR) is a critical … Read more

Generative AI has emerged as a transformative technology in healthcare, driving digital transformation in essential areas such as patient engagement and care management. It has shown potential to revolutionize how clinicians provide improved care through automated systems with diagnostic support tools that provide timely, personalized suggestions, ultimately leading to better health outcomes. For example, a … Read more

The era of perpetual AI pilots is over. This year, 65% of AWS Generative AI Innovation Center customer projects moved from concept to production—some launching in just 45 days, as AWS VP Swami Sivasubramanian shared on LinkedIn. These results come from insights gained across more than one thousand customer implementations. The Generative AI Innovation Center … Read more

Graph databases have revolutionized how organizations manage complex, interconnected data. However, specialized query languages such as Gremlin often create a barrier for teams looking to extract insights efficiently. Unlike traditional relational databases with well-defined schemas, graph databases lack a centralized schema, requiring deep technical expertise for effective querying. To address this challenge, we explore an … Read more

Over the past two years, companies have seen an increasing need to develop a project prioritization methodology for generative AI. There is no shortage of generative AI use cases to consider. Rather, companies want to evaluate the business value against the cost, level of effort, and other concerns, for a large number of potential generative … Read more

Creative teams and product developers are constantly seeking ways to streamline their workflows and reduce time to market while maintaining quality and brand consistency. This post demonstrates how to use AWS services, particularly Amazon Bedrock, to transform your creative processes through generative AI. You can implement a secure, scalable solution that accelerates your creative workflow, … Read more

In Part 1 of our series, we introduced a proactive cost management solution for Amazon Bedrock, featuring a robust cost sentry mechanism designed to enforce real-time token usage limits. We explored the core architecture, token tracking strategies, and initial budget enforcement techniques that help organizations control their generative AI expenses. Building upon that foundation, this … Read more

As organizations embrace generative AI powered by Amazon Bedrock, they face the challenge of managing costs associated with the token-based pricing model. Amazon Bedrock offers a pay-as-you-go pricing structure that can potentially lead to unexpected and excessive bills if usage is not carefully monitored. Traditional methods of cost monitoring, such as budget alerts and cost … Read more

Many enterprises are burdened with mission-critical systems built on outdated technologies that have become increasingly difficult to maintain and extend. This post demonstrates how you can use the Amazon Bedrock Converse API with Amazon Nova Premier within an agentic workflow to systematically migrate legacy C code to modern Java/Spring framework applications. By breaking down the … Read more

This post was written with Audra Devoto, Owen Janson, and Christopher Brown of Metagenomi, and Adam Perry of Tennex. A promising strategy to augment the extensive natural diversity of high value enzymes is to use generative AI, specifically protein language models (pLMs), trained on known enzymes to create orders of magnitude more predicted examples of … Read more

Deploying machine learning (ML) models into production can often be a complex and resource-intensive task, especially for customers without deep ML and DevOps expertise. Amazon SageMaker Canvas simplifies model building by offering a no-code interface, so you can create highly accurate ML models using your existing data sources and without writing a single line of … Read more

Amazon Nova Sonic is a foundation model that creates natural, human-like speech-to-speech conversations for generative AI applications, allowing users to interact with AI through voice in real-time, with capabilities for understanding tone, enabling natural flow, and performing actions. Multi-agent architecture offers a modular, robust, and scalable design pattern for production-level voice assistants. This blog post … Read more

Large-scale AI model training faces significant challenges with failure recovery and monitoring. Traditional training requires complete job restarts when even a single training process fails, resulting in additional downtime and increased costs. As training clusters expand, identifying and resolving critical issues like stalled GPUs and numerical instabilities typically requires complex custom monitoring code. With Amazon SageMaker … Read more

This post is co-written with Ross Ashworth at TP ICAP. The ability to quickly extract insights from customer relationship management systems (CRMs) and vast amounts of meeting notes can mean the difference between seizing opportunities and missing them entirely. TP ICAP faced this challenge, having thousands of vendor meeting records stored in their CRM. Using … Read more

This guest post was written by Mulay Ahmed and Caroline Lima-Lane of Principal Financial Group. The content and opinions in this post are those of the third-party authors and AWS is not responsible for the content or accuracy of this post. With US contact centers that handle millions of customer calls annually, Principal Financial Group® … Read more

Choosing the right large language model (LLM) for your use case is becoming both increasingly challenging and essential. Many teams rely on one-time (ad hoc) evaluations based on limited samples from trending models, essentially judging quality on “vibes” alone. This approach involves experimenting with a model’s responses and forming subjective opinions about its performance. However, … Read more

Generative AI is rapidly reshaping the music industry, empowering creators—regardless of skill—to create studio-quality tracks with foundation models (FMs) that personalize compositions in real time. As demand for unique, instantly generated content grows and creators seek smarter, faster tools, Splash Music collaborated with AWS to develop and scale music generation FMs, making professional music creation … Read more

Organizations often face challenges when implementing single-shot fine-tuning approaches for their generative AI models. The single-shot fine-tuning method involves selecting training data, configuring hyperparameters, and hoping the results meet expectations without the ability to make incremental adjustments. Single-shot fine-tuning frequently leads to suboptimal results and requires starting the entire process from scratch when improvements are … Read more

Artificial Intelligence (AI) is transforming the quick-service restaurant industry, particularly in drive-thru operations where efficiency and customer satisfaction intersect. Traditional systems create significant obstacles in service delivery, from staffing limitations and order accuracy issues to inconsistent customer experiences across locations. These challenges, combined with rising labor costs and demand fluctuations, have pushed the industry to … Read more

Multimodal fine-tuning represents a powerful approach for customizing vision large language models (LLMs) to excel at specific tasks that involve both visual and textual information. Although base multimodal models offer impressive general capabilities, they often fall short when faced with specialized visual tasks, domain-specific content, or output formatting requirements. Fine-tuning addresses these limitations by adapting … Read more

Since the launch of Amazon Nova at AWS re:Invent 2024, we have seen adoption trends across industries, with notable gains in operational efficiency, compliance, and customer satisfaction. With its capabilities in secure, multimodal AI and domain customization, Nova is enhancing workflows and enabling cost efficiencies across core use cases. In this post, we share four … Read more

Building AI agents that remember user interactions requires more than just storing raw conversations. While Amazon Bedrock AgentCore short-term memory captures immediate context, the real challenge lies in transforming these interactions into persistent, actionable knowledge that spans across sessions. This is the information that transforms fleeting interactions into meaningful, continuous relationships between users and AI … Read more

Training state-of-the-art large language models (LLMs) demands massive, distributed compute infrastructure. Meta’s Llama 3, for instance, ran on 16,000 NVIDIA H100 GPUs for over 30.84 million GPU hours. Amazon Elastic Kubernetes Service (Amazon EKS) is a managed service that simplifies the deployment, management, and scaling of Kubernetes clusters that can scale up to the ranges … Read more

Scala stands out as a versatile programming language that combines object-oriented and functional programming approaches. By running on the Java Virtual Machine (JVM), it maintains seamless compatibility with Java libraries while offering a concise and scalable development experience. The language has distinguished itself in the realm of distributed computing and big data processing, with the … Read more