AWSML

Every finance professional knows the drill. Monday morning arrives, and your Financial Planning and Analysis (FP&A) team disappears into data compilation. They pull numbers from multiple systems, reconcile sources, build charts, and write commentary. All to answer a question that should be straightforward: what happened with revenue last week, and why? Across AWS Finance, teams … Read more

Today, we’re excited to announce a deep-link integration between Hugging Face and Amazon SageMaker AI. Developers can now go from model discovery to hands-on experimentation in SageMaker Studio with a single selection. Whether you fine-tune a foundation model (FM) from Amazon SageMaker JumpStart or deploy it to an Amazon SageMaker Inference endpoint, you can now … Read more

Organizations deploying foundation models (FMs) often encounter a common challenge: model safeguards designed for content moderation can also prevent legitimate, business-critical use cases. A media company summarizing scripts with mature language, a cyber security firm simulating real-world threats, or a legal team processing sensitive evidence may all find that default content moderation controls deflect the … Read more

Organizations are increasingly adopting open-weight foundation models (FMs) to power production AI workloads, from agentic coding assistants to long-context document analysis. As these workloads move from experimentation to enterprise deployment, two requirements shape every model selection decision: the model must deliver the capabilities the workload demands, and the inference environment must support the organization’s security … Read more

When you build enterprise agents that execute multi-step workflows, you face a fundamental training challenge. These agents query databases, call APIs, cross-reference results, and recover from mid-process failures. The quality of any single action depends on what happens several steps later. Standard reinforcement learning from human feedback (RLHF) optimizes single responses in isolation. This approach … Read more

Sharing data internally across teams, externally with partners, or using it for workloads such as machine learning (ML) model training is fundamental to modern business operations. However, when that data contains Personally Identifiable Information (PII), organizations face significant legal and compliance obligations under regulations such as the General Data Protection Regulation (GDPR) and the Payment … Read more

Teams benchmarking generative AI models often evaluate dozens of GPU instance types, serving containers, parallelism strategies, and optimization techniques such as speculative decoding before deploying to production. Practitioners can spend weeks navigating configuration decisions and manually piecing together what they tried, what worked, and why. That complexity is exactly why we introduced optimized generative AI … Read more

Social engineering through phishing remains one of the most common tactics for launching cyberattacks. AI-generated phishing email messages now pose a new challenge for security teams managing email systems, significantly raising the risk because of their advanced sophistication. Modern social engineers use generative AI and open source intelligence (OSINT) to craft thousands of unique messages … Read more

Training a multi-turn agent in Amazon SageMaker AI to resolve support tickets or moderate content means handling a sequence of dependent steps, not a single response. These agents read instructions, make tool calls, read the results, decide the next action, and recover from a mistake before committing to an answer. That flexibility is also what … Read more

Government agencies running workloads in AWS GovCloud (US) need AI capabilities that keep pace with the commercial sector. At the same time, they can’t compromise the security and compliance controls their missions require. As open-weight foundation models (FMs) move from experimentation into mission systems, two requirements shape every model decision. First, the model must deliver … Read more

As enterprises deploy AI agents across teams, vendors, and infrastructure, managing agent-to-agent communication becomes a growing operational burden. Without a centralized layer, each new agent integration adds point-to-point connections, separate credentials, and custom routing logic. Teams spend engineering cycles wiring up connectivity instead of building agent capabilities. Access control becomes fragmented, with no single place … Read more

Let’s say your customer support agent asks for “billing issues”, and gets back technical support tickets, sales conversations with receipt issues, and billing disputes all mixed. This is the retrieval precision wall that teams hit once their agents accumulate weeks of interaction history: similarity search finds everything that’s semantically close for this customer but does … Read more

Large language models (LLMs) have transformed how we process and generate information, but they still struggle with effectively integrating knowledge across multiple sources. Standard Retrieval Augmented Generation (RAG) methods, although helpful, often fall short when tackling multi-hop reasoning tasks that require connecting information from separate documents. To address these limitations, we explore HippoRAG, a novel … Read more

This post is co-written with Conor Burke, CTO and Co-Founder at Inscribe Fraud now appears in 1 of every 16 documents, and AI-generated forgeries grew 5x from April to December 2025 (Inscribe’s 2026 State of Document Fraud Report). For financial institutions processing thousands of applications daily, this scale of deception creates an impossible challenge. Traditional … Read more

Generative AI adoption is accelerating across industries, and Amazon Bedrock provides a managed service for building production-ready AI applications. With access to more than 100 foundation models from providers such as Anthropic, OpenAI, Meta, Mistral AI, Cohere, and Amazon, teams have the flexibility to choose the right model for each use case. But choice comes … Read more

BoltzGen on Amazon SageMaker AI accelerates protein binder design by managing GPU compute infrastructure end to end. BoltzGen is a diffusion-based generative model that designs proteins and peptides capable of binding to specific biomolecular targets. A typical design campaign involves multiple GPU-intensive steps: backbone generation, inverse folding, structural validation, and candidate ranking. Running these steps … Read more

It’s our goal for AWS to be the most secure place to run any workload, and in support of that we’ve been deeply investing in security across our services since AWS’s inception more than two decades ago.  Our AI services like Amazon Bedrock are built on this foundation and with the same focus. Bedrock provides customers with … Read more

Today, we’re excited to announce the availability of Anthropic’s most advanced Sonnet model, Claude Sonnet 5, on Amazon Bedrock and Claude Platform on AWS. Claude Sonnet 5 is the first Sonnet model of Anthropic’s latest generation and represents a meaningful step forward. It delivers top-tier intelligence at Sonnet pricing for coding, agents, and everyday professional … Read more

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