6 progressive demos to detect, prevent, and self-correct AI agent hallucinations, from Graph-RAG research to production deployment on Amazon Bedrock AgentCore
-
Updated
Oct 8, 2026 - Jupyter Notebook
6 progressive demos to detect, prevent, and self-correct AI agent hallucinations, from Graph-RAG research to production deployment on Amazon Bedrock AgentCore
Generative AI document analysis on Amazon Bedrock AgentCore: a Strands agent routes pages through 27 vision specialists via an MCP Gateway, then correlates results into a structured, accessibility-oriented document tree. Eight-model registry (Anthropic, Amazon, OpenAI), specialist wizard, scripted CDK deployment, React UI on ECS with Cognito.
This repository contains hands-on labs demonstrating the capabilities of Amazon Bedrock AgentCore, a suite of services that enables you to deploy and operate highly effective AI agents securely at scale
AI STACK COMPARISON AWS AZURE GCP : A deep-dive comparison and architectural breakdown of the AI/ML and Generative AI stacks across AWS, Microsoft Azure, and Google Cloud Platform (GCP). Includes service mappings for Data Foundations, ML Development (SageMaker, Vertex AI, Azure ML), and GenAI (Bedrock, OpenAI, Gemini)
Pluggable multi-agent decision system that helps users navigate complex choices in healthcare, business, and legal domains through cognitive-emotional debate and adaptive reasoning.
The Quarkus/MicroProfile application is provisioned as an AWS Bedrock AgentCore Runtime with CDK. System tests are included. The implementation adheres to the AWS Bedrock agent runtime specifications.
Agentic AI for AWS CloudOps powered by Strands Agent, Bedrock FMs, AgentCore Runtime & Memory | Full CI/CD with Docker, Terraform & Jenkins
To associate your repository with the agentcore-sdk topic, visit your repo's landing page and select "manage topics."