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
Amazon Quick and Cisco Webex MCP servers can turn meeting prep and follow-up into a single conversational workflow. Instead of switching between Webex meetings, Vidcast videos, transcripts, recordings, and message spaces, users ask one assistant to gather the context they need. This post shows how to build a custom meeting prep and follow-up assistant using … Read more
Organizations process millions of documents daily, from insurance claims and invoices to legal contracts and medical records. While traditional optical character recognition (OCR) solutions extract text, they can’t understand context, relationships, or meaning embedded within complex documents. This limitation creates bottlenecks that require manual intervention, increasing processing time and costs while introducing potential errors. Amazon … Read more
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. The shift mirrors what my colleague Swami Sivasubramanian outlined in How Frontier Teams Are Reinventing AI-Native Development: real productivity gains come … Read more
Many companies have large volumes of paper or electronic documents that contain untapped business intelligence. With the advancement of generative AI, various large language models can be used to accurately extract relevant data from these documents. This post demonstrates an intelligent document processing pipeline that consists of both on-demand inference and batch inference options on … Read more
Teams building AI agents typically evaluate them the way they evaluate any other software: by checking whether the output matches expectations. But agents that autonomously choose tools and sequence operations across multiple sources produce behavior that output-level testing cannot fully characterize. An agent might deliver a well-structured, actionable response while hallucinating, fabricating facts because its … Read more
Amazon Quick Sight, the business intelligence capability of Amazon Quick, delivers a unified BI experience, from modern interactive dashboards and natural language querying to pixel-perfect reports, machine learning insights, and embedded analytics at scale. Amazon Quick brings together AI-powered agents for business insights, research, and automation in one integrated experience, helping teams work smarter and … Read more
Extracting structured data from unstructured documents such as invoices, contracts, tax forms, and enrollment applications is a common automation goal for organizations. Achieving high extraction precision remains a key challenge. Accuracy degrades when documents diverge from expected templates, formats vary across vendors, or scan quality is poor. With Amazon Bedrock Data Automation (BDA), you can … Read more
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. Six engineers. Seventy-six days. A project scoped for 30 developers over 12 to 18 months, delivered within a quarter. That is not hypothetical. It’s what happened when … Read more
As frontier AI models grow in scale and complexity, developers face a common challenge across every hardware platform: how do you extract the maximum performance and efficiency from the silicon their models run on. Whether delivering real-time experiences for world models, supporting deeper reasoning in agentic workflows, or reducing inference costs at scale, the gap … Read more
Managing equipment repairs for heavy farm machinery often requires technicians to diagnose issues without the right parts, leading to multiple site visits, extended downtime, and substantial financial losses, especially during harvest season. In this post, you build an AI-powered equipment repair assistant using Amazon Bedrock AgentCore that helps farmers and field technicians diagnose equipment problems, … Read more
Physical AI is moving from research into production. Robots are increasingly trained in high-fidelity simulation before being deployed to factories, warehouses, and logistics centers, because training in the real world is slow, expensive, and often unsafe, while GPU-accelerated simulation can compress months of learning into hours. This shifts the challenge to compute. Reinforcement learning (RL) … Read more
Turning multimodal first notice of loss (FNOL) evidence into tagged, decision-ready intake so adjusters start with context instead of raw artifacts. Manual FNOL processing consumes significant expert time on repetitive tasks because unstructured, multimodal evidence must be interpreted through portals designed for human interaction. Photos captured in the field, walkaround videos, scanned documents, and dictated … Read more
Incident triage is time-sensitive because site reliability engineers (SREs) and support engineers often need to collect evidence, assess user impact, and create follow-up work across separate tools. With Amazon Quick and New Relic, you can coordinate those investigation and handoff steps in a single conversational workflow. This post shows engineering teams how to apply that … Read more
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 … Read more
There’s a habit going around. Walking from one meeting to the next with the laptop cradled half-open. Sitting through a 1:1 with the lid propped just enough to keep the screen alive. Riding home while holding your laptop because it must stay running. Anywhere except closed on a desk, because closed on a desk is … Read more