This post demonstrates building an AI-powered recruitment assistant using Amazon Bedrock to enhance candidate evaluation and generate personalized interview questions. It provides data-driven insights for hiring decisions and a reference architecture for learning purposes.
This post demonstrates how to extend Kiro CLI's conversational memory by integrating a custom Model Context Protocol (MCP) server with Amazon Bedrock AgentCore Memory. This integration enables AI agents to retain information from past interactions, leading to more intelligent and context-aware conversations.
This document guides users on how to troubleshoot "Access denied" errors encountered while creating, testing, or invoking Amazon Bedrock agents. It typically involves verifying IAM permissions, resource policies, and agent-specific configurations to ensure proper access.
This post explores how Amazon Bedrock Data Automation can accurately extract information from common financial documents like bank statements and tax forms. It highlights document complexity, details custom extraction, and describes the process outcomes.
This document provides instructions on how to add cost allocation tags when invoking Amazon Bedrock on-demand models. It guides users through the process of implementing tagging for better cost management of AI services.
This post details how NarrateAI, an AI-powered conversational assistant, was built using Amazon Bedrock AgentCore to deliver business intelligence at scale for AWS SMGS. It covers the two-layer architecture, specialized AI agents for routing and validation, and key engineering patterns for production deployment.
This content explains how to build a scalable test suite for AI agents by using dataset management in Amazon Bedrock AgentCore. It emphasizes combining real-time online signals with stable offline baselines to ensure accurate agent improvement tracking over time.
Amazon Bedrock AgentCore payments is now available in preview, offering instant payments to external services without manual setup. It supports stablecoins for cost-effective microtransactions and provides configurable spending guardrails for agent budgets and transaction limits.
This post guides users through configuring Chrome enterprise policies to restrict an AI browser agent to specific websites. It demonstrates policy enforcement via session recording and custom root CA certificates, providing a solution for researching Amazon Bedrock AgentCore documentation under enterprise restrictions.
This post details the construction of a multimodal retrieval system for aerospace manufacturing documents using Amazon Nova Multimodal Embeddings on Amazon Bedrock and Amazon S3 Vectors. The system's generation quality is evaluated on 26 manufacturing queries, comparing text-only and multimodal pipelines.
This post details how Miro leveraged Amazon Bedrock to significantly improve its bug routing system. The implementation resulted in a six-fold reduction in team reassignments and a five-fold decrease in time-to-resolution, transforming the process from days to hours.
This post demonstrates how Amazon FinTech teams are using Amazon Bedrock and other AWS services to build a scalable AI application. The goal is to transform how regulatory inquiries are handled, allowing each team to maintain its own dedicated knowledge base.
This post explores design considerations for architecting multi-tenant agentic applications and the framework needed to address SaaS architecture challenges with Amazon Bedrock AgentCore.
This post details how Baz improved its AI Agent Code Review accuracy using Amazon Bedrock and Amazon Bedrock AgentCore. It covers the architectural decisions, implementation details, and business outcomes achieved by automating their code review process.
This post illustrates three methods for implementing Programmatic Tool Calling (PTC) on Amazon Bedrock. These include a self-hosted Docker sandbox on ECS, a managed solution using Amazon Bedrock AgentCore Code Interpreter, and an Anthropic SDK-compatible path.
This article details a proof-of-concept developed by Halliburton, leveraging Amazon Bedrock and generative AI to convert natural language queries into executable seismic workflows. The solution significantly accelerates workflow creation by up to 95% and offers a question-answering capability for Halliburton's Seismic Engine tools.
Amazon announced a preview of Amazon Bedrock AgentCore Payments, enabling AI agents to instantly access and pay for the services they use. This new feature was developed in partnership with Coinbase and Stripe.
Hapag-Lloyd's Digital Customer Experience and Engineering team developed a generative AI-powered feedback analysis solution. This solution, built using Amazon Bedrock, Elasticsearch, and open-source frameworks like LangChain and LangGraph, transforms customer feedback into actionable insights.
Amazon Bedrock AgentCore Browser now introduces "OS Level Actions," enabling agents to interact directly with the operating system and content visible on screen, beyond just the web layer. This new capability enhances agents' ability to observe, reason, and act by combining full-desktop screenshots with OS-level mouse and keyboard control.
This post details how to secure AI agents' access to external services using Amazon Bedrock AgentCore Identity. It specifically implements the Authorization Code Grant (3-legged OAuth) on Amazon ECS with secure session binding and scoped tokens.