11 docs tagged with "scope:design"

Architecture Decision Record documenting principles, scope, responsibilities, and rollback boundaries to be agreed upon before introducing the Self-Improving Agent Loop to production

Decision framework and pattern catalog for combining Bedrock AgentCore managed service with EKS-based self-hosted agents in hybrid deployment

Overall system architecture of a production-grade Agentic AI Platform — 6 runtime layers and 3 cross-cutting planes

Decision framework for selecting the optimal approach between SageMaker Unified Studio, Bedrock AgentCore, and EKS open architecture based on customer needs

A platform approach that reduces infrastructure operational burden using Amazon Bedrock, Strands Agents SDK, and AgentCore to focus on agent development

EKS Hybrid Nodes의 Node/Pod CIDR 라우팅 요건, CNI NAT 구성의 한계, CGNAT(100.64.0.0/10) 대역 지원, 그리고 Pod 라우팅 요건을 제거하는 Hybrid Nodes Gateway 아키텍처 분석

Guide to building Agentic AI platform using Amazon EKS and open-source ecosystem

3-plane design integrating ontology and Knowledge Graph into traditional Feature Store to reduce hallucinations, enable provenance tracking, and enhance domain entity utilization

5-stage loop design and safety mechanisms for self-hosted SLMs to autonomously learn and improve from production traces based on Karpathy's autosearch concept

Agentic AI deployment strategies that meet data sovereignty requirements — SCP region enforcement, Bedrock Geographic cross-Region inference, and EKS Hybrid Nodes-based hybrid/in-country self-hosting

5 key challenges faced when operating Agentic AI workloads