AWSML

This post is co-written by Christopher Phillippi and Chrissie Cui from Stripe. Stripe processes $1.4 trillion in annual payment volume across 50 countries, requiring compliance teams to review thousands of transactions daily. This post explores how Stripe built a production-grade AI agent system on AWS using Amazon Bedrock that reduced review handling time by 26 … Read more

The opinions expressed in this post are the authors’ views and not those of Cisco. Enterprise architectures have long been centered on REST APIs and microservices. These systems are stable, well-tested, and deeply embedded in production environments. They weren’t designed for Agent-to-Agent (A2A) communication, the emerging standard for autonomous agents that collaborate, reason, and coordinate … Read more

Optimizing model training on Amazon SageMaker AI with NVIDIA Blackwell GPUs changes what’s practical for large AI models. If you train large models today, you are likely working around a familiar set of constraints: batch sizes limited by GPU memory, sequence lengths cut short to avoid out-of-memory errors, and model sharding that adds communication overhead … Read more

As display technologies advance to higher resolutions, many organizations face a common challenge: their existing video libraries contain lower-resolution content that appears pixelated or blurry on modern high-definition displays. Traditional video upscaling approaches often struggle with computational limits, inconsistent quality, and scalability issues when processing large video collections. Many existing solutions also lack the techniques … Read more

On a typical Monday morning, an enterprise operations team receives multiple AWS Health notifications about Amazon Linux 2 end-of-life, RDS version deprecations, and EC2 instance retirements across 50+ accounts. Without self-service analytics, the team has no way to quickly identify the events that affect production systems, the events that require immediate action versus long-term planning, … Read more

When a customer service agent autonomously queries order databases, retrieves return policies, and synthesizes answers, it needs governed access to multiple data sources across your organization. Building agentic AI applications on a modern data mesh requires fine-grained access control enforced at every layer of the data interaction chain. AI agents that autonomously discover database schemas, … Read more

When your document repository contains hundreds of millions of files accumulated over nearly a decade, how do you systematically find and redact sensitive customer data without taking years to complete? This was the challenge facing The Huntington National Bank (Huntington), a top 10 bank in the United States. Redacting sensitive information at scale Since 2015, … Read more

If you run a clinic or hospital network, you already know the cost of missed appointments. The average no-show rate across US healthcare sits between 5–30 percent, depending on specialty. Each empty slot represents lost revenue, idle provider time, and delayed patient care. The standard fix, calling patients one by one to confirm or reschedule, … Read more

One dashboard shows 42,000 active movie view counts while another shows 38,500. Your chat agent references a third number entirely. Data teams spend hours reconciling numbers instead of answering strategic questions, and trust in analytics erodes. This is a pattern that we see across many organizations. Teams spend more effort reconciling numbers than actually using … Read more

Loka transformed customer voice interactions by building a conversational AI agent with Amazon Nova 2 Sonic that keeps customers engaged with natural, responsive experiences. Their AWS-based solution achieves high speech reasoning accuracy on Big Bench Audio while delivering significantly lower costs and faster response times than traditional voice AI pipelines. In this post, we demonstrate … Read more

Protein researchers face a time-consuming challenge: manually searching through thousands of peptide sequences to find structurally similar candidates is slow, error-prone, and requires deep domain expertise to interpret results. Building a protein research copilot can transform how researchers search for structurally similar peptides across large datasets — enabling natural language queries, automated embedding generation, and … Read more

Building multi-tenant AI applications presents new architectural challenges. You need complete tenant isolation between customers, different service tiers with different capabilities, granular cost tracking, and observability per tenant. Without these, you could risk exposing customer data, not providing appropriate quality of service to your customers or running up unforeseen costs. In this post, you will … Read more

This post was co-written with Kevin Jones from Ampersend (Edge & Node) and Chethan Shriyan from the Amazon Bedrock AgentCore Payments team. Ampersend and Amazon Bedrock AgentCore Payments are addressing one of the hardest problems in agentic AI. How do autonomous agents pay for services without developers building bespoke billing integrations, credential management, and payment … Read more

Turning a library of aerial imagery into a natural-language-searchable knowledge base is a problem that touches every industry that relies on geospatial data — insurance, real estate, government, infrastructure, and agriculture. The traditional path requires either manual tile-by-tile inspection or training a bespoke computer vision model for each new question. Multimodal embeddings, large language model … Read more

With ComfyUI workflows on Amazon SageMaker AI processing jobs, you can automate content generation at scale. For enterprises, every delay or misstep in creating compelling multimedia assets can mean lost sales, faded brand relevance, or missed marketing deadlines. When a product launch deadline looms or a seasonal promotion needs urgent assets, waiting for designers to … Read more

AI agents are changing how organizations find and act on information, but they share one structural limitation: their knowledge is frozen at training time. When you ask an agent that relies only on its training data about today’s stock price, a sports score, or a release that shipped an hour ago, it can’t respond. Web … Read more

Amazon Quick and Adobe Marketing Agent help marketing teams access campaign insights within governed conversations in seconds. Marketers can ask questions about campaign performance, audiences, journeys, campaign conflicts, and content performance in natural language. Amazon Quick provides the chat experience and action orchestration. Adobe provides marketing-domain analysis to the approved data sources behind those questions. … Read more

Monitoring and troubleshooting generative AI inference endpoints operating at scale is challenging. When your large language model (LLM) endpoint’s P99 latency spikes, you must determine in minutes whether the root cause is GPU memory pressure, a saturated KV cache, unbalanced traffic across Availability Zones, or an auto scaling policy that hasn’t triggered. The shift from … Read more

A year ago, Simon Willison wrote one of the cleanest definitions of an agent that has stuck around: An LLM agent runs tools in a loop to achieve a goal. That definition stuck because it describes what every production agent actually does. Kiro, Amazon Q Developer, Quick Agents, Codex, Claude Code: under the hood, they … Read more

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. For payloads up to 128,000 bytes, this removes an entire network … Read more

What if you came back from a full day of meetings and the busywork was already done? Stalled deals followed up on. Compliance changes summarized. Meeting prep written. Not because you multi-tasked, but because something was working in the background while you focused on other urgent priorities. Teams are already using Amazon Quick — an AI assistant that connects to your most-used apps … Read more

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 … Read more

The models powering today’s agents are remarkably capable. They can reason across complex problems, plan multi-step workflows, and generate nuanced responses. But most agents are operating well below that potential. The gap isn’t intelligence. It’s access to the right context and feedback. A customer service agent tasked with answering a question about your company’s refund … Read more

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. The new InvokeGuardrailChecks API gives you the flexibility to invoke supported safeguards at any turn in the agentic loop … Read more

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. Over the years, Amazon SageMaker AI has continued to reduce latency across these scaling stages: detecting … Read more

As large language models (LLMs) grow in size and complexity, maximizing inference throughput while minimizing latency remains a critical challenge for enterprise production deployments. Speculative decoding is one effective strategy to address this, utilizing a lightweight draft model to guess future tokens which are then verified by the target LLM in a single forward pass. While state-of-the-art frameworks like Extrapolation Algorithm for Greater … Read more

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, … Read more

When your AI agent fails in production, knowing that it failed is only the beginning. The harder question is why it failed and what to fix. Traditional evaluation tells you “this agent scored 60 percent on goal completion,” but leaves you manually reviewing execution traces to understand what went wrong. For teams operating agents at … Read more

A common challenge in AI-powered research workflows is depth versus context. If your agent reads ten web pages, its context window (the amount of text a large language model (LLM) can process at once) gets filled with raw content. If it also runs data analysis code, chart-generation logic competes with strategic reasoning for limited space. … Read more

Rocket Close is a Detroit-based title agency and appraisal management company within Rocket Companies that provides title insurance, property valuation, and settlement services. As demand for mortgages and loans grew, title operations became a bottleneck in the homebuying process. Time-intensive, state-specific title examinations, combined with manual research and fragmented systems, slowed throughput and made it … Read more