Goal
The path to "LLMOps"
Here is the reading path leading up to this book, derived from its dependencies and ordered from the fundamentals.
The path so far (9 books)
Why read this first: Where 'The DevOps Handbook' preaches collaboration between development and operations, Google's 'Site Reliability Engineering' shows the concrete form of solving the operations side 'with software engineering'. With error budgets and SLOs to engineer reliability, it is a natural evolution of DevOps.
Why read this first: After mastering basic Kubernetes usage, the next stage is learning established solutions to recurring design problems on top of it. Ibryam & Huß's 'Kubernetes Patterns' provides a pattern language—sidecars, health checks, and more—for correctly designing cloud-native applications on K8s.
Why read this first: After learning the patterns for correctly designing apps on K8s in 'Kubernetes Patterns', move to the field knowledge of keeping them running in production. 'Cloud Native DevOps with Kubernetes' connects design patterns to actual operations—monitoring, scaling, incident response—closing the gap between design and operation.
Why read this first: Operating many microservices on K8s, traditional monitoring can no longer trace 'where and what happened'. 'Observability Engineering' makes the internal state of distributed systems visible via distributed tracing and structured events, providing the observation capability essential to cloud-native operation.
Why read this first: After designing 'watch predefined metrics' monitoring with Julian's 'Practical Monitoring', advance to observability, which lets you explore even unknown failures. Majors et al.'s 'Observability Engineering' explains systems where high-cardinality events let you ask 'why did it happen?' after the fact, going beyond the limits of monitoring.
Why read this first: After implementing stability patterns like circuit breakers from Nygard's 'Release It!', you must observe whether they actually work in production. 'Observability Engineering' makes the activation of those patterns and the system's internal behavior visible, making it verifiable that the 'unbreakable design' is functioning.
Why read this first: Where 'Site Reliability Engineering' articulates principles distilled from Google's practice, its sequel 'The Site Reliability Workbook' shows 'how to implement it at your own company' with concrete procedures and case studies. Theory first, then the implementation volume—a required progression.
Why read this first: Once you put SLOs into operation with 'The Site Reliability Workbook', you need a foundation to measure SLIs accurately and trace the causes of violations. 'Observability Engineering' provides that measurement-and-investigation foundation, concretizing the observation infrastructure that supports SLO-based operations.
Why read this first: Where 'Observability Engineering' teaches observability for distributed systems in general via structured events and distributed tracing, 'LLMOps' applies that thinking to running LLM-based applications, connecting it to LLM-specific observation challenges like evaluation-metric design and early detection of hallucination.
Sources