This post is a collaboration between AWS and the OpenClaw Foundation. Autonomous agents that browse the web, call APIs, and query Model Context Protocol (MCP) servers can encounter services that require an HTTP 402 Payment Required response to be settled before access continues. To use those services without pausing for a human at every transaction, … Read more
In multi-turn reinforcement learning (RL), your custom reward function decides what the model actually learns. A subtly wrong reward can quietly teach the wrong thing while every training curve looks healthy. Designing a reward that holds up over multi-turn, agentic tasks is one of the hardest parts of customizing Amazon Nova models. For multi-turn training, … Read more
A common challenge in building agentic workflows is mixing managed foundation models (FMs) with your own cost-optimized or domain-specific models, without rewriting your agent framework to do it. In this post, we show you how to combine OpenAI-compatible endpoints on Amazon SageMaker AI with Amazon Bedrock AgentCore runtime, a capability of Amazon Bedrock AgentCore, and … Read more
When you deploy AI agents built with frameworks like Strands Agents, LangGraph, and CrewAI, you need observability into their performance. This holds true whether they run on Amazon Elastic Kubernetes Service (Amazon EKS), Amazon Elastic Container Service (Amazon ECS), AWS Lambda, on-premises, or another cloud provider such as Google Cloud Platform (GCP) or Microsoft Azure. … Read more
Enterprises across healthcare, manufacturing, retail, and financial services struggle to automate legacy web applications that demand human-like interaction beyond what standard Robotic Process Automation (RPA) can provide at scale. Amazon Bedrock AgentCore Browser Tool, combined with Strands Agents, addresses this gap with a fully managed browser service that lets AI agents drive these legacy interfaces … Read more
Mergers and acquisitions (M&A) teams face a persistent challenge: conducting thorough due diligence on multiple acquisition targets while maintaining speed and analytical rigor. Teams often spend weeks manually reviewing targets before identifying viable opportunities. Amazon Bedrock AgentCore is a platform to build, connect, and optimize agents at scale, with any framework or model. It can … Read more
Your enterprise data lives in dozens of systems, but often the work happens in Microsoft 365. Amazon Quick bridges that gap as an AI assistant grounded in your data, now available directly inside Microsoft Word, Excel, PowerPoint, and Outlook. These extensions don’t require you to adopt a new application or change how you work. Instead, … Read more
Part 1 introduced granular cost attribution for Amazon Bedrock. This feature automatically traces every inference request back to the IAM principal that made the call. It showed how the new line_item_iam_principal column can give you per-user and per-application visibility. With optional cost allocation tags, you can also aggregate spend by team, project, or tenant using … Read more
This post is co-authored with OneAdvanced team Deploying AI agents on a United Kingdom (UK)-sovereign AWS architecture requires careful decisions about model hosting, data residency, and agent orchestration. OneAdvanced, a UK-based enterprise software provider serving over 10,000 customers, needed to deliver AI capabilities while making sure that no data would leave the UK. At the … Read more
This post is co-written with Patrick Duffy from Solv Labs and Houman Shadab from ICME Labs Solv Labs built an AI agent-payments workflow using Amazon Bedrock AgentCore payments, a capability of Amazon Bedrock AgentCore, governed by two layers: ORACLE (Solv’s policy engine) and ICME PreFlight for compliance verification. AgentCore payments provides the payment processing infrastructure. … Read more
Running large language model (LLM) inference at scale typically forces a KV cache trade-off: you either pay for oversized GPU instances to accommodate a growing KV cache, or you accept slow time-to-first-token (TTFT) as identical prompts get recomputed on every request. For teams deploying a broad catalog of publicly available foundation models (FMs), such as … Read more
Cyber defenders have never had more capability at their fingertips, and they have never needed it more. Frontier models can now reason across an entire code base, trace a vulnerability to its root cause, and propose a fix in minutes. Those same capabilities are available to adversaries. This is why the window between a vulnerability … Read more
This post was co-written by ONESTRUCTION, Inc. and Amazon Web Services Japan G.K. as part of GENIAC (Generative AI Accelerator Challenge) Phase 3, with technical advisory from the AWS Generative AI Innovation Center (GenAIIC). Building domain-specialized foundation models in data-scarce fields is hard. You need enough training data, specialized knowledge, and ways to verify your … Read more
This post is co-written with Ry Rainey and Graham Gibson from Pixieset. Photographers and artists are among the most skeptical audiences for generative AI. They have watched it threaten their craft and flood their industry with synthetic work. A 2025 MIT study found 95% of enterprise Generative AI pilots deliver zero measurable returns. Pixieset is … Read more
This post is co-written with Mark Himelfarb and Garrett Wilkerson from First Orion. First Orion’s engineering teams were shipping faster than quality assurance (QA) could test, until Amazon Nova Act transformed QA automation. As a branded communications company whose solutions reach hundreds of millions of phone calls across carriers in the US, Canada, UK, and … Read more
AI administrators deploying Claude Code and Claude Desktop across their workforce need centralized controls over authentication, model access, cost attribution, and spend enforcement. These controls reduce operational overhead and apply governance consistently at scale. Claude apps gateway provides a self-hosted governance layer between these applications and Amazon Bedrock or Claude Platform on AWS. Building on … Read more
To power up AI workflows on Amazon Elastic Kubernetes Service (Amazon EKS), data scientists need interactive IDEs like JupyterLab and Code Editor. Yet running those IDEs usually means leaving the cluster that hosts their pipelines, moving to a standalone JupyterHub deployment or a local laptop. That switch leaves them without the GPU nodes, shared storage, … Read more
nOps, an AI-powered cloud optimization solution, recently reimagined its Financial Operations (FinOps) analytics capabilities by transitioning to Amazon Bedrock AgentCore. Amazon Bedrock AgentCore is a service to build, connect, and optimize agents at scale, with any framework or model. The new foundation helps nOps better serve customers managing commitment optimization across Amazon Web Services (AWS), … Read more
Prior authorization is the approval process health plans require before covering certain medical services or medications. It remains one of the most manual processes in healthcare, not because the medical reasoning for requiring approval is flawed, but because the policies that govern it are trapped in static, unstructured formats that resist automation. This content is … Read more
This is a guest post co-written with Vitaly Omelchenko from the TReNDS Center at Georgia State University. At the Center for Translational Research in Neuroimaging and Data Science (TReNDS), a joint center of Georgia State University, Georgia Institute of Technology, and Emory University, we develop and apply advanced analytical methods and neuroinformatics tools for brain … Read more
As the National Hockey League (NHL) regular season enters its final stretch each spring, one question dominates the minds of hockey fans: has my team clinched the playoffs? The answer is often surprisingly hard to discern. With 32 teams, complex tie-breaking rules, and hundreds of remaining games, determining whether a team is mathematically guaranteed a … Read more
Before AI agents, it was generally sufficient for access controls to treat each action as an independent event. Applications relied on deterministic business logic to enforce whether actions happened in the right order or whether the data was up-to-date. AI agents behave in fundamentally different ways than traditional applications. They decide at runtime which tools … Read more
Amazon Bedrock AgentCore gateway is a fully managed, serverless AI gateway that provides a single, secure entry point for AI traffic. AgentCore gateway routes traffic to tools such as managed web search, managed knowledge bases, MCP servers, inference models (LLMs), agents (A2A, agents as tools, etc.), or HTTP endpoint. Today, we are announcing support for … Read more
Agents are becoming more autonomous and teams are running more of them, but trust and security have not kept pace. According to McKinsey, roughly 80% of organizations have already encountered risky behavior from AI agents. As a result, security and risk concerns are the leading barrier to scaling agentic AI (McKinsey’s State of AI Trust … Read more
As organizations move from experimenting with coding agents to adopting them across engineering teams, the leadership question changes. It is no longer only, “Can this tool help a developer?” It becomes, “How do we understand adoption, manage consumption, maintain reliability, and scale access responsibly?”. Codex can emit OpenTelemetry (OTel) metrics about its activity. When local … Read more
A US-headquartered global organization recently came to us with a deceptively simple data-residency request: let their engineers use Claude Code. The requirement: Amazon Bedrock model inference had to be processed in London (the eu-west-2 AWS Region), not merely called from London. Their compliance team had drawn a hard line. Prompts, completions, and intermediate processing were … Read more
Teams that adopt Amazon Bedrock Automated Reasoning checks often want to run the policy lifecycle in code. Running it in code keeps the work repeatable, reviewable, and driven by the coding agent they already use. Authoring a good Automated Reasoning policy has a learning curve, and the lifecycle has constraints that can trip you up. … Read more
Many enterprises have a long tail of internal tools that never get built. A team needs a shipping-cost calculator, a straightforward intake form, a small dashboard over a spreadsheet, but each one requires a developer, a backlog slot, and a deployment pipeline. The tools are too small to prioritize and too numerous to ignore. PDI … Read more
Buying a home is one of the biggest financial decisions most people face, and LendingTree built a multi-agent mortgage assistant on Amazon Bedrock to make the process more straightforward. The assistant educates borrowers, understands their situation, and provides tailored options in a natural conversation. Borrowers must weigh purchase or refinance, conventional or government-backed, 15-year or … Read more
What if deploying production-grade AI agents required zero infrastructure management, came with enterprise observability built-in, and worked easily with your existing on-premises systems? Mobileye, the autonomous driving pioneer with more than 230 million EyeQ system-on-chips deployed across roughly 1,200 vehicle models worldwide, saw an opportunity to free skilled engineers from routine internal ticket status inquiries. … Read more