22 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)

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

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

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

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

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

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.

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)

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

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

CloudWatch Network Flow Monitor 에이전트의 내부 동작을 해부합니다. eBPF sock_ops 콜백 수집, 유저스페이스 집계와 Kubernetes enrichment, OTLP 전송 경로, EKS add-on 배포와 데이터 미표시 3계층 진단

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.

AI platform monitoring, observability, evaluation, compliance, and domain-specific operations guide

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.

RAG pipeline quality evaluation and continuous improvement using Ragas

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.