Today, we are excited to announce the availability of Open AI’s new open weight GPT OSS models, gpt-oss-120b and gpt-oss-20b, from OpenAI in Amazon SageMaker JumpStart. With this launch, you can now deploy OpenAI’s newest reasoning models to build, experiment, and responsibly scale your generative AI ideas on AWS. In this post, we demonstrate how … Read more
Amazon Q Business is a fully managed, generative AI-powered assistant that helps enterprises unlock the value of their data and knowledge. With Amazon Q Business, you can quickly find answers to questions, generate summaries and content, and complete tasks by using the information and expertise stored across your company’s various data sources and enterprise systems. … Read more
Picture this: Your team just received 10,000 customer feedback responses. The traditional approach? Weeks of manual analysis. But what if AI could not only analyze this feedback but also validate its own work? Welcome to the world of large language model (LLM) jury systems deployed using Amazon Bedrock. As more organizations embrace generative AI, particularly … Read more
The education sector needs efficient, high-quality course material development that can keep pace with rapidly evolving knowledge domains. Faculty invest days to create content and quizzes for topics to be taught in weeks. Increased faculty engagement in manual content creation creates a time deficit for innovation in teaching, inconsistent course material, and a poor experience … Read more
Handmade.com is a leading hand-crafts product marketplace, offering unique, seller-contributed items to customers around the world. With over 60,000 products in the catalog and some percentage of listings containing basic descriptions that could be improved for better search and search engine optimization (SEO) performance, the need for automation became evident. Manual processing, consuming on average … Read more
Organizations serving multiple tenants through AI applications face a common challenge: how to track, analyze, and optimize model usage across different customer segments. Although Amazon Bedrock provides powerful foundation models (FMs) through its Converse API, the true business value emerges when you can connect model interactions to specific tenants, users, and use cases. Using the … Read more
At AWS Summit New York City 2025, Amazon Web Services (AWS) announced the preview of Amazon Bedrock AgentCore browser tool, a fully managed, pre-built cloud-based browser. This tool enables generative AI agents to interact seamlessly with websites. It addresses two fundamental limitations: first, foundation models (FMs) are trained on large but static datasets and need … Read more
AI agents have reached a critical inflection point where their ability to generate sophisticated code exceeds the capacity to execute it safely in production environments. Organizations deploying agentic AI face a fundamental dilemma: although large language models (LLMs) can produce complex code scripts, mathematical analyses, and data visualizations, executing this AI-generated code introduces significant security … Read more
This post is co-written with Rich Young from Arize AI. Agentic AI applications built on agentic workflows differ from traditional workloads in one important way: they’re nondeterministic. That is, they can produce different results with the same input. This is because the large language models (LLMs) they’re based on use probabilities when generating each token. … Read more
IT teams face mounting challenges as they manage increasingly complex infrastructure and applications, often spending countless hours manually identifying operational issues, troubleshooting problems, and performing repetitive maintenance tasks. This operational burden diverts valuable technical resources from innovation and strategic initiatives. Artificial intelligence for IT operations (AIOps) presents a transformative solution, using AI to automate operational … Read more
Organizations can optimize their migration and modernization projects by streamlining the containerization process for legacy applications. With the right tools and approaches, teams can transform traditional applications into containerized solutions efficiently, reducing the time spent on manual coding, testing, and debugging while enhancing developer productivity and accelerating time-to-market. During containerization initiatives, organizations can address compatibility, … Read more
Picture this: your machine learning (ML) team has a promising model to train and experiments to run for their generative AI project, but they’re waiting for GPU availability. The ML scientists spend time monitoring instance availability, coordinating with teammates over shared resources, and managing infrastructure allocation. Simultaneously, your infrastructure administrators spend significant time trying to … Read more
Developers building AI applications face a common challenge: converting unstructured data into structured formats. Structured output is critical for machine-to-machine communication use cases, because this enables downstream use cases to more effectively consume and process the generated outputs. Whether it’s extracting information from documents, creating assistants that fetch data from APIs, or developing agents that … Read more
As organizations seek to derive greater value from their AWS Support data, operational teams are looking for ways to transform raw support cases and health events into actionable insights. While traditional analytics tools can provide basic reporting capabilities, teams need more sophisticated solutions that can understand and process natural language queries about their operational data. … Read more
The Amazon Strands Agents SDK is an open source framework for building AI agents that emphasizes a model-driven approach. Instead of hardcoding complex task flows, Strands uses the reasoning abilities of modern large language models (LLMs) to handle planning and tool usage autonomously. Developers can create an agent with a prompt (defining the agent’s role … Read more
“Tavily is now available on AWS Marketplace and integrates natively with Amazon Bedrock AgentCore Gateway. This makes it even faster for developers and enterprises to embed real-time web intelligence into secure, AWS-powered agents.” As enterprises accelerate their AI adoption, the demand for agent frameworks that can autonomously gather, process, and synthesize information has increased. Traditional … Read more
Organizations across various sectors face significant challenges when converting meeting recordings or recorded presentations into structured documentation. The process of creating handouts from presentations requires lots of manual effort, such as reviewing recordings to identify slide transitions, transcribing spoken content, capturing and organizing screenshots, synchronizing visual elements with speaker notes, and formatting content. These challenges … Read more
Customers are increasingly looking to use the power of large language models (LLMs) to solve real-world problems. However, bridging the gap between these LLMs and practical applications has been a challenge. AI agents have appeared as an innovative technology that bridges this gap. The foundation models (FMs) available through Amazon Bedrock serve as the cognitive … Read more
Today, we’re excited to announce that Mistral-Small-3.2-24B-Instruct-2506—a 24-billion-parameter large language model (LLM) from Mistral AI that’s optimized for enhanced instruction following and reduced repetition errors—is available for customers through Amazon SageMaker JumpStart and Amazon Bedrock Marketplace. Amazon Bedrock Marketplace is a capability in Amazon Bedrock that developers can use to discover, test, and use over … Read more
Financial regulations and compliance are constantly changing, and automation of compliance reporting has emerged as a game changer in the financial industry. Amazon Web Services (AWS) generative AI solutions offer a seamless and efficient approach to automate this reporting process. The integration of AWS generative AI into the compliance framework not only enhances efficiency but … Read more
Fine-tuning of large language models (LLMs) has emerged as a crucial technique for organizations seeking to adapt powerful foundation models (FMs) to their specific needs. Rather than training models from scratch—a process that can cost millions of dollars and require extensive computational resources—companies can customize existing models with domain-specific data at a fraction of the … Read more
This post is co-written with Abhinav Pandey from Nippon Life India Asset Management Ltd. Accurate information retrieval through generative AI-powered assistants is a popular use case for enterprises. To reduce hallucination and improve overall accuracy, Retrieval Augmented Generation (RAG) remains the most commonly used method to retrieve reliable and accurate responses that use enterprise data … Read more
Drug discovery is a complex, time-intensive process that requires researchers to navigate vast amounts of scientific literature, clinical trial data, and molecular databases. Life science customers like Genentech and AstraZeneca are using AI agents and other generative AI tools to increase the speed of scientific discovery. Builders at these organizations are already using the fully … Read more
In early 2025, we introduced the Amazon Nova Act SDK as a research preview to help developers build agents that reliably complete tasks in a web browser. Now, we are excited to work with customers to take their agents to production in a limited preview, using new AWS integrations including AWS Identity and Access Management … Read more
This post is co-written with Jessie Jiao from Crypto.com. Crypto.com is a crypto exchange and comprehensive trading service serving 140 million users in 90 countries. To improve the service quality of Crypto.com, the firm implemented generative AI-powered assistant services on AWS. Modern AI assistants—artificial intelligence systems designed to interact with users through natural language, answer … Read more
Building modern serverless applications on AWS requires navigating best practices to manage the integration between multiple services, such as AWS Lambda, Amazon API Gateway, Amazon DynamoDB, and Amazon EventBridge. Security considerations, performance optimization, and implementing a comprehensive monitoring systems adds further requirements to build a serverless architecture while adhering to AWS best practices. Amazon Q Developer CLI with Model Context Protocol … Read more
Legal teams spend bulk of their time manually reviewing documents during eDiscovery. This process involves analyzing electronically stored information across emails, contracts, financial records, and collaboration systems for legal proceedings. This manual approach creates significant bottlenecks: attorneys must identify privileged communications, assess legal risks, extract contractual obligations, and maintain regulatory compliance across thousands of documents … Read more
This post is co-written with Bogdan Arsenie and Nick Mattei from PerformLine. PerformLine operates within the marketing compliance industry, a specialized subset of the broader compliance software market, which includes various compliance solutions like anti-money laundering (AML), know your customer (KYC), and others. Specifically, marketing compliance refers to adhering to regulations and guidelines set by … Read more
Cold start in recommendation systems goes beyond just new user or new item problems—it’s the complete absence of personalized signals at launch. When someone first arrives, or when fresh content appears, there’s no behavioral history to tell the engine what they care about, so everyone ends up in broad generic segments. That not only dampens … Read more
Large language models (LLMs) have rapidly evolved, becoming integral to applications ranging from conversational AI to complex reasoning tasks. However, as models grow in size and capability, effectively evaluating their performance has become increasingly challenging. Traditional benchmarking metrics like perplexity and BLEU scores often fail to capture the nuances of real-world interactions, making human-aligned evaluation … Read more