AI agents can do more than chat. With the right protocol, an agent can render an interactive chart inline in your conversation, update a shared canvas in real time, or pause mid-execution to ask for your approval before proceeding. These interactions (generative UI, shared state, and human-in-the-loop) need a standard way for agent backends to … Read more
Managing AI model access across dozens or hundreds of AWS accounts creates a dilemma. Either you grant AWS Marketplace permissions broadly, risking governance issues, or you manually enable subscriptions in each account. For organizations using third-party models like Anthropic Claude or Cohere, this operational overhead slows AI adoption. In this post, we show you how … Read more
Implementing resilience patterns for large language model (LLM) inference is critical as generative AI workloads move from experimentation to production at scale. With LLM powered apps now in production, organizations need ways to keep LLM inference highly available, responsive, and cost-effective at scale. Existing resilience best practices like static stability and implementing backoffs and retries … Read more
This post was co-written with Tim Chauncey and Dheeraj Bhadani of Outpost VFX. AI model training for visual effects (VFX) can take weeks, creating bottlenecks in production timelines. For Outpost VFX, which operates studios across the UK, Canada, and India delivering high-end film and episodic content, every day of delay impacts client deliverables and project … Read more
IBS Software’s Cargo system processes thousands of bilingual cargo logistics email messages daily. The system extracts critical information such as air waybill (AWB) numbers, flight details, weights, and delivery instructions in both English and Japanese. This added to the complexity of building a robust Named Entity Recognition (NER) solution. Challenges included manual intervention that slowed … Read more
Amazon Quick Sight is a core feature within Amazon Quick — an agentic, AI-powered digital workspace designed to maximize end-user productivity— that provides AI-powered BI capabilities through natural language queries, interactive dashboards, and embedded analytics from trusted enterprise data sources. Amazon Quick Sight assets such as dashboards, analyses, datasets, and data sources can be backed up using the … Read more
A scanned yearbook page contains 176 printed names, 4 portrait photographs, and zero machine-readable structure linking them. To digitize this page, you need reliable photo detection with bounding boxes and accurate name extraction. You also need a way to determine which name belongs to which face based on page layout. In this post, we show … Read more
At PAR Technology Corporation, we build technology for the restaurant industry, supporting over 300 restaurant businesses, from independent operators to large, multi-brand franchise groups. Across this diverse customer base, we help organizations make better decisions by unlocking the value of their data. When we set out to build a natural language text-to-SQL agent for self-serve … Read more
Manually processing paper-based forms remains a significant cost in the healthcare industry. Despite advancements in data extraction of scanned documents and images, human oversight is usually still needed. Entry error by the individual creating the form or lower-confidence extractions from the digitization still must be remediated. In this post, we show you how to build … Read more
Production artificial intelligence (AI) agents can fail silently. They may return plausible but incorrect answers, enter infinite reasoning loops, or select the wrong tools without triggering error alerts. These failures make debugging production agent behavior difficult because standard logs and metrics do not capture how decisions are made. Amazon Bedrock AgentCore Observability addresses these debugging … Read more
Picture this: a compliance officer needs a specific clause during an audit, an attorney needs contract terms while a client waits on the phone, or a finance analyst needs numbers from last quarter’s report before a meeting that starts in 10 minutes. In each case, waiting for a scheduled job to finish is not practical. … Read more
Insurance is an $8 trillion global industry burdened by manual workflows and a growing talent shortage. Cara delivers an AI-native solution on AWS that automates back-office processes for insurance brokerages. Insurance agents routinely spend hours on repetitive tasks. These include completing applications, analyzing policy coverages, re-keying data across systems, and relaying information between clients and … Read more
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