Today, we’re announcing inline payload support for Amazon SageMaker AI Async Inference. Customers can now send inference payloads directly in the request body of the InvokeEndpointAsync API, removing the need to upload input data to Amazon Simple Storage Service (Amazon S3) before each invocation.

Today, Quick gets even more powerful: new autonomous agents that work continuously on your behalf, an activity feed that helps you prioritize your most important work, and the ability to find insights across every data source your business runs on from a single question.

Agents are only as intelligent as the context they can reason over. Today, that context is scattered across data lakes, data warehouses, lakehouses, databases, and streams, and in institutional knowledge that has never been written down. You want to trust the decisions made by your AI agents, but that can't happen until agents have context. Imagine what becomes possible when we give agents a safe way to access the context they need to deliver trusted decisions. This is why at the AWS Summit New York City, we’re announcing a series of innovations that deliver intelligence for your data and AI agents at scale.

Today we're introducing new capabilities on Amazon Bedrock AgentCore, the platform to build, connect, and optimize agents. In this post, we cover how these capabilities close each gap: connecting agents to organizational, web, and paid knowledge; helping teams find and fix what's going wrong in production; and enforcing controls that scale as agents grow more capable. Together, they help you build more capable agents faster, govern them with controls that scale, and improve them continuously.

Today, we’re announcing a new API with Amazon Bedrock Guardrails. With this API, you can apply individual safeguards, also referred to as safety checks, at any point in your agentic AI applications without creating guardrail resources. In this post, we walk through how the InvokeGuardrailChecks API works and how to use it to build safe, multi-turn agentic AI applications.

Today, we’re excited to announce container image caching for Amazon SageMaker AI inference, the next major advancement in our faster scaling optimization journey. This speeds up end-to-end latency by up to 2x for generative AI models during scale-out events.

This post walks you through how to use P-EAGLE directly within Amazon SageMaker AI. It will demonstrate how to select a compatible model from the SageMaker JumpStart catalog, configure the parallel drafting specifications, and deploy a highly optimized real-time SageMaker AI endpoint to accelerate your generative AI applications.

Today, we are announcing the availability of the Gemma 4 family on Amazon Bedrock. Built by Google DeepMind and released under the Apache 2.0 license, Gemma 4 is a family of open-weight models designed with a focus on intelligence-per-parameter across a broad range of deployment scenarios. The family includes three instruction-tuned variants: Gemma 4 31B, Gemma 4 26B-A4B, and Gemma 4 E2B. These cover dense and mixture-of-experts (MoE) architectures, where only a fraction of the model’s parameters activate per request. The variants offer built-in reasoning, native function calling, and multimodal input across text and image.

In this post, we walk you through calling the detector functions to diagnose real agent failures. You learn how to interpret their structured output: categorized failures with confidence scores, causal chains linking root causes to downstream symptoms, and fix recommendations specifying whether a change belongs in your system prompt or tool definitions. You also learn how to integrate detection into your evaluation pipeline for automated diagnosis on every test run.

In this post, you'll build a competitive research agent that demonstrates this pattern end to end. This walkthrough targets developers building multi-step AI workflows who need isolated execution environments for their agents. In Part 2 of the notebook, you can deploy this same agent to Bedrock AgentCore Runtime using the AgentCore CLI, so it runs as a managed, session-isolated service.

In this post, we explore how Rocket Close built a solution using Strands Agents, large language models (LLMs), Amazon Bedrock, Amazon Bedrock Knowledge Bases, and Model Context Protocol (MCP) tools. We cover solution features, the rationale for the technology stack, lessons learned, and the business impact at Rocket Close.

This post shows how to build a custom meeting prep and follow-up assistant using Amazon Quick and Cisco Webex MCP servers. From a single prompt, the agent finds an upcoming Webex meeting, reviews prior meeting summaries and transcripts, and pulls related Vidcast highlights and transcript context. It then searches Webex message threads for unresolved follow-ups and creates a concise prep brief. After the meeting, the same assistant can summarize the discussion and identify action items. It can also find related Vidcast updates and draft a follow-up message for the right Webex space.

This post outlines the development of a cost-effective and scalable intelligent document processing pipeline on AWS, powered by Amazon Bedrock and its features. BDA is a managed service within Amazon Bedrock that automates the extraction of insights from documents. We demonstrate how BDA extracts and analyzes document content, while Strands Agent hosted on Amazon Bedrock AgentCore Runtime coordinate specialized processing tasks, and Amazon Bedrock Knowledge Base enable contextual understanding across multiple documents. By combining these capabilities within a unified architecture, organizations can transform their document processing workflows with minimal development effort.

AWS Professional Services (AWS ProServe) compressed engagement timelines from months to days, not by adding artificial intelligence (AI) tools to an existing process, but by fundamentally rebuilding how we deliver from the inside out. In this post, we share how AWS ProServe became a frontier team, the practices that enabled it, and what your engineering organization can take from our experience.

This post demonstrates an intelligent document processing pipeline that consists of both on-demand inference and batch inference options on Amazon Bedrock to enable the flexibility on the document processing time and cost.

Agent-EvalKit is an open-source toolkit (Apache 2.0) that makes this evaluation infrastructure available by integrating with AI coding assistants, including Claude Code, Kiro CLI, and Kilo Code. This post walks through how Agent-EvalKit works across its six evaluation phases, using a travel research agent built with the Strands Agents SDK and Amazon Bedrock as a running example.

Today, we’re excited to announce two new capabilities that make Quick Sight dashboards even more expressive and business-aligned: sparklines and custom sort for controls. In this post, we walk through both features, what they are, when to use them, and how to configure them, with real-world scenarios that bring them together in a practical, decision-ready dashboard.

Blueprint instruction optimization is a BDA feature that automatically refines your extraction instructions to address this challenge directly. You provide three to ten example documents with expected values, and BDA refines your blueprint instructions to improve accuracy in minutes, not weeks. No separate model fine-tuning is required. By the end of this post, you can optimize your blueprints to improve accuracy, run the optimization workflow through the Amazon Bedrock console or the API, and apply best practices for selecting examples and ground truth.

Frontier teams are not just using AI to code faster. They’re redesigning how software gets built. The result is 4.5x productivity gains, in some cases more than 10x.

Today, we’re announcing the Neuron Agentic Development capabilities: a collection of AI agents and skills that make this possible for developers building on AWS Trainium and AWS Inferentia. In this post, we explain how the Neuron Agentic Development capabilities accelerate the kernel development workflow.

In this post, you build an AI-powered equipment repair assistant using Amazon Bedrock AgentCore that helps farmers and field technicians diagnose equipment problems, identify required parts, and access manufacturer-approved repair procedures through natural language. The solution uses AgentCore Runtime with the Strands Agents SDK, Amazon Nova 2 Lite as the foundation model, Amazon Bedrock Knowledge Base for retrieval-augmented generation (RAG), and AgentCore Memory for conversation persistence.

In this post, we show how to train robot policies for the Unitree H1 humanoid with NVIDIA Isaac Lab on Amazon SageMaker AI across two compute options: Amazon SageMaker HyperPod and Amazon SageMaker Training Jobs.

In this post, we demonstrate how a hands-free FNOL intake system combines agents built with the Strands Agents SDK for domain reasoning with Amazon Bedrock AgentCore Browser Tool for live portal interaction. This approach preserves human expertise while removing repetitive screen work.

This post shows engineering teams how to apply that principle to one of the most time-sensitive workflows in engineering: incident triage. You will build a custom incident triage assistant agent using Amazon Quick that orchestrates a response with the New Relic Model Context Protocol (MCP) Server and Asana through native integrations. From a single prompt, the Amazon Quick agent investigates the incident, assembles a root cause analysis (RCA) brief with evidence links, and creates a tracked Asana task ready for handoff.

With access to the latest generative AI models and high-performance accelerated compute in high global demand, AWS customers need tools to take advantage of model availability and capacity across multiple AWS Regions, while still meeting their security and privacy requirements. cross-Region Inference (CRIS) on Amazon Bedrock meets these needs by automatically routing requests across multiple […]

Amazon Bedrock AgentCore Runtime gives each agent session its own isolated microVM with a persistent workspace, secure tool access through Gateway, and built-in observability—so you can run Claude Code, Codex, Kiro, and Cursor in parallel without sharing secrets, ports, or filesystems. Close the lid, go to dinner, and pick up where you left off tomorrow.

In this post, we introduce mathematical optimization, explain how it fits within the broader AI landscape, and showcase real-world success stories where the Innovation Center has partnered with customers to deliver concrete results.

This blog has previously discussed FHE for ML inference in the post Enable fully homomorphic encryption with Amazon SageMaker endpoints for secure, real-time inferencing, but this post goes a little further. That previous post showed how to implement FHE-based inference 'from scratch' by hand-crafting a linear-regression algorithm using a low-level library called SEAL. Instead, this post shows a much more flexible and higher-level approach based on concrete-ml, a high-level library built specifically for FHE-based inference. It supports several common types of models 'out of the box' and is even API compatible with the well-known ML library scikit-learn.

In this post, we cover the structure of Amazon Quick ARNs and provide a practical mental model for working with them. By the end, you can look at an ARN and immediately understand what it means for your migration strategy, diagnose permission issues faster, and design multi-tenant architectures with confidence.

In this post, we walk you through the Nova Sonic Test Harness, an open source framework that we built to solve both problems. It serves as a rapid iteration tool for tuning system prompts and tool configurations (run a conversation, see results, adjust, repeat) and as a comprehensive evaluation framework for validating voice agent quality at scale. It runs complete multi-turn conversations with Amazon Nova Sonic automatically, evaluates them using LLM-as-judge techniques, and can even detect cases where the model’s audio output doesn’t match its text output (audio hallucinations). No microphone required.

Deploy NVIDIA Nemotron 3 Ultra on Amazon SageMaker JumpStart. Get 5x faster inference and 30% lower cost for agentic AI workloads with this frontier reasoning model.

In this post, we introduce Amazon Bedrock Ops Alert, a three-layer automated monitoring solution that proactively detects operational issues, dynamically adjusts alarm thresholds, classifies alarms by category, automatically creates context-aware support cases, helps prevent duplicate cases when an unresolved case of the same alarm category is already active, and delivers contextualized notifications to AI SRE teams. We walk through the solution architecture and how you can deploy it in your own environment.

In this post, we show you how to get started with NEXUS on Amazon SageMaker JumpStart, walk through the deployment process, and demonstrate how to run predictions against your enterprise datasets.

In this post, we look at how to use SOCI on publicly available Deep Learning AMIs and Containers, when to use the various SOCI modes provided by the tool, and how to quickly and efficiently use this tool in your workloads today.

In this post, you learn how to use Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO) together to improve the tool-calling accuracy of a small language model (SLM). The example uses Amazon SageMaker AI training jobs, so you can focus on training code instead of managing your own training infrastructure. You also learn how to evaluate tool-calling accuracy and compare a base model to several fine-tuned variants, so you can make data-driven decisions about model quality.

Fine-tuning for domain-specific tasks means improving performance in one area without degrading the model’s general capabilities, and getting that balance right is harder than it looks. This post walks through how to navigate that balance, from selecting the right customization strategy for your data and task, to configuring the training parameters that most influence outcomes, like learning rate, batch size, and checkpointing. We also cover the common mistakes that lead to wasted training runs and how to catch them early, so you can improve domain performance without degrading general capabilities or burning through compute on avoidable failures. By the end, you will know how to improve domain performance without degrading general capabilities and how to avoid the expensive failures that come from getting the balance wrong.

In this post, we'll walk through implementing object detection with Amazon Nova 2 Lite. You'll learn how to deploy an object detection application using Amazon Bedrock, AWS Lambda, and Amazon API Gateway. You'll also learn how to craft effective prompts, process structured JSON output, and visualize results. We explore practical applications across manufacturing, agriculture, and logistics.

This post walks through how Baz built their Spec Review agent using Amazon Bedrock and Amazon Bedrock AgentCore. We'll cover the architecture decisions, implementation details, and the business outcomes they achieved by leveraging these AWS services to automate their code review process

This post demonstrates how to implement Open Authorization (OAuth) Code flow as an inbound authorization mechanism for MCP servers hosted on Amazon Bedrock AgentCore Gateway. By the end of this guide, you will have a production-ready setup where each AI assistant request is authenticated with a valid user identity token issued from your organization’s identity provider.

Today, we’re excited to announce the ability to reference a secret in AWS Secrets Manager for AgentCore Identity, so you can reference your own preconfigured secret from Secrets Manager and retain full control over how it is managed. With this ability, you can extend your organization’s existing secrets governance processes to AgentCore. You can provide an existing, preconfigured AWS Secrets Manager secret to use with your credential provider resources. You retain full control over its encryption configuration, rotation, replication, tags, and resource policies, just as you would manage other secrets in Secrets Manager. You can also choose a secret from another AWS account within the same AWS Region, though cross-Region secret sharing isn’t supported. This also supports secrets brought in through AWS Secrets Manager external connectors, enabling integration with third-party secret managers.

In this post, we walk through how to use Amazon Quick Research to integrate biomedical data sources for rare cancer research. The walkthrough uses pediatric sarcoma as the research domain and draws on publicly available datasets from PubMed and other open biomedical repositories. It covers the end-to-end workflow: defining a research objective, configuring data sources, reviewing the AI-generated research plan, running the investigation, and iterating on results using the revision and versioning system.

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.

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 […]

In this post, we use a lakehouse data agent to demonstrate how you can use Policy for deterministic access control and Lambda interceptors for dynamic validation. We then show how to combine Lambda interceptors and Policy to implement a geography-based access control which requires both dynamic validation and deterministic access control.

In this post, we address several key risks that surface when designing an agentic payment system, and how to address them with the capabilities of AgentCore payments.

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 deploying, managing, and continuously improving AI agents in production.

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 […]

In this post, we walk through a practical implementation using KDB-X MCP server integration with Amazon Quick, demonstrating how traders and analysts can ask questions using conversational language and receive actionable insights from datasets. You can apply this same integration pattern across various domains, from financial market analysis to IoT sensor monitoring to DevOps performance dashboards, where you need to simplify access to time series insights.

This post demonstrates a comprehensive observability solution using Amazon Managed Grafana dashboards that provides a holistic view of both quality and quantity for LLMs served on Amazon SageMaker AI endpoints with inference components.

Azercell Telecom LLC, Azerbaijan's leading telecommunications provider, wanted to build an Azerbaijani large language model (LLM) on Amazon SageMaker AI for telecom use cases and a customer-facing chatbot. The challenge: adapting foundation models (FMs) to a morphologically rich language with limited training data and no existing blueprint for efficient LLM training in Azerbaijani. In a six-week collaboration, Azercell worked with the AWS Generative AI Innovation Center to establish a production-ready framework on Amazon SageMaker AI.