73 docs tagged with "scope:ops"

Guide for declaratively defining agent workflows like IaC and automating compliance

Agent operations KPIs including task success rate, tool-call accuracy, hallucination rate, cost per interaction, escalation rate, and Langfuse·OTel schema

Langfuse-based agent monitoring operations — monitoring architecture, key metrics, PromQL, alerting, and cost tracking (for tool comparison, see LLMOps Observability)

LLM Gateway-level Guardrails — PII redaction, prompt injection defense, content filtering, tool comparison, and Korean financial compliance mapping

LLM Gateway-level multi-tenancy strategy — LiteLLM virtual key hierarchical model vs Kong Consumer policy comparison, budget enforcement, 3-tier tenant isolation (gateway, data, observability)

Review probe optimization examples that use observability data and AI.

AIDLC Checkpoint Approval gates and ISO 8601-based audit logs — Implementation guide for AIDLC audit trails in regulated industries

AI Agent-based autonomous incident response — Strands/Kagent integration, Chaos Engineering + AI, ontology feedback loop

Guide to tuning Inference Gateway Cascade Routing classification thresholds, Canary rollout, Fallback, and cost drift alerts based on production traces

Review patterns for terminating in-flight requests and connections.

Review image builds, pre-pulling, and startup time comparisons.

Strengthening supply chain security through container image signing, SBOM, and CI/CD security gates

Guide to diagnosing and resolving EKS control plane issues

Why the same workload shows different CPU utilization across instance sizes and generations, which KPIs to compare instead, where throttling and scheduling wait are observed, a Pod sizing baseline, and how to decide on mixed node pools.

Architecture patterns and decision guide for achieving high availability through object replication in EKS multi-cluster environments

Review pre-deployment checks and the complete reference list.

Guide to improving technical domain coding quality with LoRA Fine-tuning, VectorRAG, and GraphRAG — including FSI SI production scenarios

Authentication/Authorization best practices for Non-Standard Callers (CI/CD, monitoring, automation) accessing the EKS API Server

Review probe and shutdown configurations in Auto Mode environments.

Debugging guide for EKS Auto Mode environments

Understand EKS Control Plane internals and learn Provisioned Control Plane usage, monitoring strategies, and CRD design best practices for stable scaling of CRD-based platforms

Root cause analysis, recovery procedures, and prevention strategies for Control Plane access loss caused by deleting the default namespace in an EKS cluster.

Explore examples of integrating probes with EKS features.

Architecture patterns and operational strategies for achieving high availability and fault tolerance in Amazon EKS environments

Architecture, deployment strategies, limitations, and best practices for the AWS EKS Node Monitoring Agent that automatically detects and reports node health issues

Detailed parameters by PCP tier, APF seat calculation formulas, large-scale cluster sizing examples, ClusterLoader2 performance validation methodology, public AWS-reported benchmark context, and hypothetical sizing examples

CPU/Memory resource configuration, QoS classes, VPA/HPA autoscaling, and resource right-sizing strategies for Kubernetes Pods

Kubernetes Pod scheduling strategies, Affinity/Anti-Affinity, PDB, Priority/Preemption, Taints/Tolerations best practices

Compliance guide mapping SOC2, ISO27001, Electronic Financial Supervisory Regulation (전자금융감독규정), and ISMS-P to AI operations

Review startup, health check, and shutdown configuration for Fargate.

GitOps architecture, KRO/ACK usage, multi-cluster management strategies and automation for stable large-scale EKS cluster operations

Debugging guide for GPU/AI workloads on EKS

EKS threat detection and response using Amazon GuardDuty Extended Threat Detection

The Network Flow Monitor agent's TCP callbacks, userspace aggregation, Kubernetes metadata, OTLP publishing, and EKS troubleshooting.

Zero-trust access control based on EKS Pod Identity and IRSA migration guide

Compare initialization tasks and sidecar configurations.

How Pod IPs on EKS consume subnet addresses, VPC NAU, and branch ENI limits, and how to keep Karpenter's instance-size fallback from turning into IP exhaustion through NodePool and VPC CNI settings.

Declarative AI agent management architecture and orchestration patterns in Kubernetes using Kagent

Review Pod termination during node replacement and scale-down.

Node provisioning, scaling signals, readiness, and cost validation with Karpenter v1.13 and EKS Auto Mode

In-depth debugging guide for the Karpenter autoscaler

A framework guide covering the DRA core model (DeviceClass, ResourceClaim, ResourceSlice), resource types beyond GPUs (NICs, interconnects, FPGAs), and adoption criteria

Covers the 1-hour TTL constraint of EKS Kubernetes events, export pipeline design, and AI Agent query architecture based on the EKS and CloudWatch MCP servers.

Kubernetes policy management and governance based on Kyverno v1.17

FinOps guidance for Amazon EKS cost allocation and optimization with SCAD, CUR 2.0, Karpenter v1.13, tagging, per-container rightsizing, and ROI verification.

LLM platform FinOps methodology — token metering, showback/chargeback strategies, agentic cost models, budget policies, and gateway integration

LLMOps observability tool comparison — Langfuse·LangSmith·Helicone·CloudWatch selection criteria and hybrid architecture (for Langfuse operations, see Agent Monitoring)

Connect load balancer health checks with Pod Readiness Gates.

Deploying Milvus vector database on Amazon EKS and integrating with RAG pipelines

Connect cache efficiency, KV capacity, latency, and routing across seven observability layers, with explicit delivery, evaluation coverage, and quality gates.

Orchestrator-Worker, Voting, Debate, Hierarchical Supervisor patterns and LangGraph/CrewAI/AutoGen/Strands Agents SDK implementation

Guide to diagnosing EKS networking issues - VPC CNI, DNS, Service, NetworkPolicy

Review configuration for managing node infrastructure readiness.

Guide to diagnosing and resolving EKS node issues

EKS observability stack configuration and incident detection strategies - Container Insights, Prometheus, ADOT

Observability implementation guide for EKS Hybrid Nodes — covers Cluster Insights configuration self-diagnosis, CloudWatch Container Insights hybrid configuration (RUN_WITH_IRSA), NVIDIA GPU metric integration, a Cilium Hubble-based eBPF dashboard, and Network Flow Monitor applicability analysis.

The data foundation of AIDLC Operations — building 3-Pillar observability + AI analysis layer

Operational best practices for EKS Hybrid Nodes — mixed mode workload placement, configuration validation with Cluster Insights and nodeadm debug, monitoring architecture, and cost optimization based on tiered vCPU-hour billing.

Review the execution flow and examples for PostStart and PreStop.

Review the flow from a termination request to container shutdown.

ML-based predictive scaling and anomaly detection — Karpenter+AI, CloudWatch Anomaly Detection, AI Right-Sizing

Define cached-token, turn-gap, and preemption data contracts, correlation limits, and non-inferiority quality gates for prefix cache tuning.

Examine unnecessary restarts and incorrect health check configurations.

Review examples for REST, gRPC, batch, JVM, and AI workloads.

Review probe types, mechanisms, and timing together.

Guide to diagnosing outages caused by mechanism differences and timeout mismatches between K8s Probes and ALB/NLB/Ingress Controller Health Checks

RAG pipeline quality evaluation and continuous improvement using Ragas

ROSA cluster installation demo - STS-based cluster creation, IAM role configuration, autoscaling setup, and admin access configuration guide

A design for validating identity, permissions, MFA, login restrictions, and session controls across Hybrid Cloud Console, AWS, and OpenShift

Review application shutdown handling examples.

Guide to diagnosing EKS storage issues - EBS/EFS CSI Driver, PVC mount failures

Kubernetes version upgrade strategy for EKS Hybrid Nodes — covers how nodeadm upgrade works, the mandatory manual cordon/drain, handling SSM signing key expiration (nodeadm 1.0.19+), private mirror configuration for air-gapped networks, and the upgrade runbook.

Guide to diagnosing EKS workload issues - Pod state-based debugging, deployment failure patterns, probe configuration