AWSML

The science of optimal decisions — and how leading organizations are applying it. Every enterprise faces decisions that are too complex for intuition or manual decision-making alone. Which delivery routes minimize cost while meeting next-day promises? How should hundreds of robots sequence movements across a factory floor without collision? How do you staff a 24/7 … Read more

Machine learning (ML) inference often requires processing sensitive data—medical records, proprietary business information, or personal communications. What if you could run ML inference in the cloud while hiding your data from the cloud itself? More specifically, what if you could enforce that your data stayed encrypted throughout the entire ML inference process? This post will … Read more

You migrate dashboards from development to production, but the permissions don’t carry over. You share a dashboard with your Finance team, but they keep getting “access denied.” You set up namespaces for multi-tenant isolation, and the same username works in one namespace but not another. These are real tasks that Amazon Quick administrators tackle regularly, … Read more

Today, we are excited to announce the day-zero availability of NVIDIA Nemotron 3 Ultra on Amazon SageMaker JumpStart. With this launch, you can now deploy the Nemotron 3 Ultra model using a one-click deployment experience. Nemotron 3 Ultra is an open model built for frontier reasoning and orchestration in long-running autonomous agents, delivering 5x faster … Read more

Amazon Bedrock powers generative AI for more than 100,000 organizations worldwide—from startups to global enterprises across every industry. It provides the proven infrastructure and comprehensive capabilities to confidently build applications and agents that work in production with the flexibility, enterprise security, and proven scalability you need to innovate boldly and deliver AI that drives real … Read more

Today, we’re announcing support for Fundamental’s NEXUS model on Amazon SageMaker AI. With this launch, you can deploy a foundation model (FM) purpose-built for tabular data prediction. This model helps your enterprise generate accurate, deterministic predictions from structured data in days instead of months. In this post, we show you how to get started with … Read more

Deep Learning AMI and AWS Deep Learning Containers are now enabled with support for SOCI snapshotter and index. Seekable OCI (SOCI) is a technology that enables efficient container image management through selective file downloading. It uses a layer-based indexing system to map file locations within container images, allowing containers to start with only the necessary … Read more

AI agents can autonomously handle complex, multi-step tasks, but their effectiveness depends on calling the right tools to retrieve information or take action. When an agent picks the wrong tool, formats parameters incorrectly, or breaks a workflow chain, task completion times grow, error rates rise, support costs increase, and user experiences degrade. As more organizations … Read more

Large language models (LLMs) deliver strong results on general tasks, but they often struggle with specialized work that requires understanding proprietary data, internal processes, or domain-specific terminology. Amazon Nova Forge addresses this by enabling you to build your own frontier models using Amazon Nova. You can start development from early model checkpoints, blend proprietary data … Read more

Traditional computer vision solutions can require significant upfront investment. Setting up data pipelines, model training infrastructure, compute resources, and a dedicated data science team is often prohibitive for small companies or teams. Amazon Nova 2 Lite, available through Amazon Bedrock, provides an appealing alternative solution. This multimodal foundation model detects objects through natural language prompts … Read more

Code review was always manual and ineffective because of the inherent disconnect between code and product. Developers could review whether code compiled and worked, but not whether it fulfilled all functional and design requirements. In the past, QA teams spent hours manually clicking through preview environments to ensure features behaved as expected, and even more … Read more

In modern development workflows, developers increasingly rely on agentic coding assistants such as Kiro Integrated Development Environment (IDE) to interact with remote tools and services. However, organizations require robust authentication mechanisms to provide secure, identity-verified access between these agentic coding assistants and enterprise Model Context Protocol (MCP) servers. Amazon Bedrock AgentCore is a fully managed … Read more

AI agents are only as powerful as the tools they can access. Whether retrieving customer data from a CRM, posting updates to Slack, or querying a GitHub repository, agents need to call external APIs, and that means securely passing credentials at runtime. Getting that right, without hardcoding secrets in code or exposing them in agent … Read more

Rare cancer research generates heterogeneous data across genomic sequencing pipelines, clinical trial registries, biomarker repositories, and peer-reviewed literature. Integrating these sources for a single investigation typically requires custom ETL pipelines, manual schema reconciliation, and iterative querying across disconnected systems—a process that can take weeks before any analysis begins. Amazon Quick Research addresses this integration challenge … Read more

GPT-5.5, GPT-5.4, and Codex are now generally available on Amazon Bedrock. Deploy them in production applications and agents today, on Bedrock’s high performance inference engine. Key takeaways  GPT-5.5, the most advanced frontier model from OpenAI, is generally available on Amazon Bedrock. Pricing matches OpenAI first-party rates. Codex on Amazon Bedrock is generally available with pay-per-token pricing. Inference runs through Bedrock, and … Read more

While deploying Model Context Protocol (MCP) servers in production, enterprises need fine-grained access control across servers, observability into which teams use which tools, security guarantees against data exfiltration, and centralized credential management, all at scale. Amazon Bedrock AgentCore Gateway sits between MCP servers and the clients that consume them, centralizing credential management, observability, and secure … Read more

Securing AI agent behavior is a key customer challenge in building agentic solutions. As enterprises rapidly adopt AI agents to automate workflows, they face a scaling challenge in managing secure access to tools across the organization. Modern unified enterprise AI platforms have hundreds of agents serving users across the organization. These agents need to access … Read more

Agents increasingly take actions on behalf of their end users, whether that’s selecting tools, browsing the web, and calling MCP servers autonomously to achieve a goal. When the tools, MCP endpoints, or web resources an agent reaches are paid, the agent gets stuck without the ability to transact. Amazon Bedrock AgentCore payments, announced in preview … Read more

When you build agentic AI solutions, you face unique operational challenges. Agents make unpredictable decisions, costs spiral unexpectedly, and debugging non-deterministic failures seems impossible. Agentic AI applications don’t just execute predetermined workflows. They reason, adapt, and make autonomous decisions, and DevOps practices need to be adapted. That’s where AgentOps comes in, the operational discipline for … Read more

If you’re iterating on deploying large language models (LLMs) on AWS GPU instances, you’ve probably noticed the larger the model to be loaded into GPU High Bandwidth Memory (HBM), the longer the painful wait until the GPUs are ready for inference. As models grow to hundreds of billions of parameters and GPU environments grow ever … Read more

Model Context Protocol (MCP) integration in Amazon Quick transforms how financial analysts access time-series market intelligence, removing the need for complex database queries. As a financial analyst, you navigate millions of stock trades flowing through markets every second, searching for patterns that drive trading decisions. Financial institutions often use time series databases to analyze high-frequency … Read more

Deploying large language models (LLMs) at scale on Amazon SageMaker AI Inference makes observability a critical pillar of any production machine learning (ML) strategy. Unlike conventional software that returns deterministic outputs, LLMs generate variable, free-form responses that are difficult to validate with standard metrics. LLM output quality can change over time as input distributions shift, … Read more

This solution builds on open source tools including PyTorch, Hugging Face Transformers, and Liger Kernels. The authors would also like to thank Aiham Taleb, Arefeh Ghahvechi, Manav Choudhary, Rohit Thekkanal, Daz Akbarov, Jamila Jamilova, Ross Povelikin, Almas Moldakanov, Christelle Xu, and Ivan Khvostishkov for their contributions in making this project possible. Azercell Telecom LLC, Azerbaijan’s … Read more

As ML teams grow, embedding Amazon SageMaker AI MLflow Apps into a custom portal requires a scalable approach to access management. Distributing presigned URLs doesn’t scale for teams with dozens of data scientists, and granting individual AWS Management Console access adds operational overhead for administrators managing access controls. Teams who rely on SSO-integrated internal portals … Read more

Machine learning (ML) teams use MLflow to manage their ML lifecycle effectively. Amazon SageMaker MLflow provides comprehensive ML experiment tracking and model management capabilities. However, many enterprises have existing infrastructure requirements that need HTTPS-based integrations rather than direct SDK usage. Many organizations need to integrate Amazon SageMaker MLflow with their established systems while maintaining their … Read more

This post was co-authored with Karan Singh, Head of Partnerships at LangChain Validating AI agent behavior before production is one of the hardest problems in applied AI. Agents are non-deterministic, multi-step where errors in early steps can affect downstream results. A single bad tool call can cascade through an entire workflow. LangSmith on AWS gives … Read more

Agent evaluation is most powerful when you combine fast-moving online signals with stable offline baselines. To understand whether your agent is truly improving over time, you need a fixed benchmark alongside your changing real-world traffic. Managing test cases for evaluation baselines as a dataset in Amazon Bedrock AgentCore brings the discipline of versioned test fixtures … Read more

Today, we’re excited to announce the availability of Anthropic’s most advanced Opus model, Claude Opus 4.8, on Amazon Bedrock and the Claude Platform on AWS. Claude Opus 4.8 represents a meaningful step forward, delivering improvements across the workflows teams run in production, from agentic coding and deep knowledge work to multi-stage autonomous tasks that span … Read more

Financial institutions running on AWS and Snowflake benefit from a deeply integrated framework that combines Snowflake’s AI Data Cloud with AWS cloud infrastructure, including integrations with AWS services such as Amazon Simple Storage Service (Amazon S3), AWS Glue, Amazon SageMaker, and Amazon Bedrock. With over 50 native integrations between AWS services and Snowflake, organizations can … Read more

Financial institutions process thousands of documents daily, including tax forms, loan statements, and purchase orders. Each has a unique format, structure, and field names, making it challenging to create automation workflows using optical character recognition (OCR) software. Amazon Bedrock Data Automation (BDA) helps solve these challenges by automating the extraction, validation, and analysis of data … Read more