AWS for Industries

Category: Amazon Bedrock

Physical AI Production Designer: Cell Programming from Weeks to Hours

Programming a single robotic production cell can take weeks, and complex operations can include hundreds of cells. Today, we’re announcing Physical AI Production Designer on AWS, a new AWS solution that helps manufacturing and automation engineers reduce robot cell programming time. Instead of programming each robot by hand, engineers define the production task from their […]

Building a Frictionless Insurance Advisor with Amazon Bedrock AgentCore

Building a Frictionless Insurance Advisor with Amazon Bedrock AgentCore

Frictionless Insurance Advisor is an AI-powered advisory tool built end to end on Amazon Bedrock AgentCore. Advisors answer customer questions on the spot, compare products across providers, identify coverage gaps, and start applications that fill from the conversation, with compliance controls enforced in code.

How to make four specialist AI agents act as one trusted financial advisor

How to make four specialist AI agents act as one trusted financial advisor

When you split a banking assistant into specialist AI agents on separate runtimes, they lose their shared state. This post shows architects how we built the Connected Finance demo on Amazon Bedrock AgentCore: carrying shared context across runtimes, discovering specialists at runtime, and applying one set of guardrails to voice and text.

Accelerate design space exploration with AI on AWS

Accelerate design space exploration with AI on AWS

Engineers rarely validate more than a handful of designs because each physics-based simulation can take days to months. This post walks through a multi-agent Design Space Explorer on Amazon Bedrock AgentCore and the Strands Agents SDK that uses generative AI and ML surrogate models to evaluate car designs across disciplines in minutes.

How Oldcastle APG Automates 13 Million Order Lines with Amazon Bedrock

This post was co-written with Avdhesh Paliwal of Oldcastle APG. Oldcastle APG uses Amazon Bedrock to automate 13 million manual order lines, reducing order processing time from hours to minutes. In the first two weeks of production, the system processed over 10,000 order lines with a 95% automation rate. A team of 2 developers and […]

How CTBC Bank modernizes mainframe reverse engineering with a multi-agent pipeline on Amazon Bedrock AgentCore

How CTBC Bank modernizes mainframe reverse engineering with a multi-agent pipeline on Amazon Bedrock AgentCore

CTBC Bank moved COBOL reverse engineering for its core-system modernization from a single AI agent to a governed multi-agent pipeline on Amazon Bedrock AgentCore. A Supervisor coordinates seven single-responsibility sub-agents with quality gates checked in code, delivering an about fourfold efficiency gain with the audit trail a regulated bank needs.

Reinventing software delivery with AI-SDLC on Amazon Bedrock AgentCore

Reinventing software delivery with AI-SDLC on Amazon Bedrock AgentCore

Verisk partnered with AWS to build AI-SDLC: specialized AI agents spanning requirements, grooming, development, code review, and QA on Amazon Bedrock and Amazon Bedrock AgentCore, with people reviewing and approving the work at each stage. See the architecture, early productivity gains, and lessons from a regulated insurance environment.

How BMW builds toward Industry AI on Amazon SageMaker AI

How BMW builds toward Industry AI on Amazon SageMaker AI

BMW Group is building toward Industry AI on Amazon SageMaker AI by fine-tuning task-specific LoRA adapters on engineering process data and serving multiple domain capabilities from a single endpoint. Large language models (LLMs) produce convincing output on general tasks, but company-internal engineering processes, proprietary taxonomies, and domain-specific quality standards aren’t represented in public training corpora. Prompting with rules and examples doesn’t reliably close this gap when a task imposes many hard constraints simultaneously because the model has no training signal telling it which constraints are inviolable. In this post, we describe the architecture, walk through the results, and present a repeatable framework you can apply to your own domain.

How to prepare for the proposed HIPAA Security Rule update with AWS Backup and the HIPAA Assistant

How to prepare for the proposed HIPAA Security Rule update with AWS Backup and the HIPAA Assistant

In this post, we summarize what HHS has proposed, when it is likely to matter, and how to use Amazon Web Services (AWS) to close the gaps now. We cover how AWS Backup maps to the three proposed backup and recovery obligations, and we introduce the HIPAA Assistant, an open source sample from AWS that reviews your infrastructure-as-code and application code for Security Rule gaps and cites each finding to the exact paragraph of the regulation.

AI-enabled ECU validation on AWS using Corellium Atlas virtual ECUs

AI-enabled ECU validation on AWS using Corellium Atlas virtual ECUs

Automotive firmware teams face a structural bottleneck: physical electronic control unit (ECU) hardware doesn’t scale at the pace of software development. Waiting for hardware access creates delayed test cycles, late defect detection, and limited parallel coverage across Software Defined Vehicle (SDV) programs.