All series

Contents

Table of contents

Read in order or enter through the topic you need today.

08 volumes

Showing 1-8 of 8

  1. Vol.01LLM FoundationsTokenizer behavior, model families, embeddings, inference, context windows, and what model capabilities actually mean.0 chapters100+ planned
  2. Vol.02Context EngineeringPrompt systems, structured context, memory, tool instructions, compression, and reliable multi-turn behavior.0 chapters120+ planned
  3. Vol.03RAG SystemsRetrieval architecture from chunking and ranking to citations, freshness, permissions, and production tuning.0 chapters150+ planned
  4. Vol.04Agents and ToolsTool calling, planning loops, MCP-style integrations, task decomposition, and controlled autonomy.0 chapters150+ planned
  5. Vol.05Evals and QualityGolden datasets, rubric grading, regression suites, adversarial tests, human review, and release gates.0 chapters120+ planned
  6. Vol.06AI Platform OpsLatency, cost, caching, routing, observability, tracing, batch workflows, and deployment patterns for AI apps.0 chapters120+ planned
  7. Vol.07AI SecurityPrompt injection, tool abuse, data leakage, model supply chain, policy controls, and safe fallback design.0 chapters100+ planned
  8. Vol.08AI Product SystemsChoosing AI use cases, designing human-in-the-loop flows, measuring value, and avoiding demo-only products.0 chapters140+ planned
References, profiles, and topics
#ai-engineering#llms#rag#agents#evals