Agentic DevOps with Claude Code: Build governed AI platforms on Kubernetes with GitOps, observability, and self-service workflows
暫譯: 使用 Claude Code 實踐 Agentic DevOps：在 Kubernetes 上以 GitOps、可觀測性與自助服務工作流程打造受治理的 AI 平台

Build and validate a governed AI-native developer platform with Claude, Kubernetes, GitOps, policy controls, observability, and reproducible workflows.

Key Features:

- Control Claude with specifications, permissions, tests, and auditable workflows

- Build governed agent and model infrastructure on Kubernetes with GitOps

- Create a Backstage self-service path from developer request to traced agent

- Purchase of the print or Kindle book includes a free PDF eBook

Book Description:

Build agentic DevOps workflows without bypassing the controls your Kubernetes platform already depends on. This book shows you how to use Claude as a controlled platform-engineering worker while introducing agents, model serving, and developer self-service through reproducible GitOps workflows, explicit trust boundaries, policy checks, and testable completion gates.

You'll establish a cloud-native foundation with Argo CD, cert-manager, OpenBao, External Secrets Operator, Kyverno, Prometheus, Grafana, Loki, Tempo, and OpenTelemetry. You'll then add governed AI traffic using Gateway API, kgateway, agentgateway, kagent, MCP tools, and LLM Guard before serving an OpenAI-compatible model with KServe and vLLM.

The hands-on approach shows you how to constrain Claude with specifications, permissions, audit hooks, tests, and Git checkpoints. You'll trace agent and model activity, diagnose failures from evidence, and turn operational fixes into reusable tests. You'll also build a Backstage template and Argo CD ApplicationSet that provide a governed path from developer request to running agent.

By the end of the book, you'll be able to build and validate an AI-native internal developer platform in phases, route agent and model activity through existing platform controls, and prepare the architecture for production use.

What You Will Learn:

- Control Claude with specifications, permissions, and test gates

- Design an AI-native IDP with clear ownership and trust boundaries

- Build a reproducible Kubernetes foundation with Argo CD

- Trace platform, agent, and model activity with OpenTelemetry

- Govern LLM, MCP, and agent traffic through shared gateways

- Run Kubernetes-native agents with guardrails and policy controls

- Serve OpenAI-compatible models using KServe and vLLM

- Build a governed Backstage self-service path for agent services

Who this book is for:

Platform engineers, DevOps engineers, SREs, cloud engineers, and platform architects who want to use Claude to build and operate governed AI capabilities on Kubernetes. Engineering and technical leads can also use the architecture and production guidance to assess scope and risk. Experience with Kubernetes, Helm, and GitOps is required; prior Backstage experience is not.

Table of Contents

- Designing an AI-Native Internal Developer Platform

- Governing Claude Code with Specifications, Tests, and Permissions

- Bootstrapping the GitOps Foundation

- Building the Platform Observability Plane

- Delivering the Developer Portal and Platform Extensions

- Creating a Governed Gateway for Agent Traffic

- Running Agents as Kubernetes Resources

- Serving and Observing Models on Kubernetes

- Shipping a Governed Self-Service Golden Path

- Enforcing Governance and Taking the Platform to Production