diff --git a/FOCUS Architecture - EN_ Feature-Oriented, Clean, Unidirectional and Scalable Architecture.pdf b/FOCUS Architecture - EN_ Feature-Oriented, Clean, Unidirectional and Scalable Architecture.pdf new file mode 100644 index 0000000..a312a54 Binary files /dev/null and b/FOCUS Architecture - EN_ Feature-Oriented, Clean, Unidirectional and Scalable Architecture.pdf differ diff --git a/MEMORY.md b/MEMORY.md index 4d3b946..389fa79 100644 --- a/MEMORY.md +++ b/MEMORY.md @@ -1,5 +1,28 @@ # Reading Memory Log +## Context Engineering: Engineering Information for AI Systems — J.C. Ködel +- **Status**: In Progress +- **Current Position**: Chapter 1 of 36 read; active-recall review awaiting reader responses +- **Folder**: /library/Context Engineering/ +- **Source File**: /library/Context Engineering/source-file.pdf +- **Structure**: 36 top-level sections; Sections 1–2 are orientation and the technical argument begins in Section 3; contents indexed in /library/Context Engineering/book-structure.md +- **Current Notes**: /library/Context Engineering/Chapter-01/chapter-notes.md +- **Last Updated**: 2026-10-01 + +### Chapter Index + +#### Chapter 1 — About the Author +- Notes File: /library/Context Engineering/Chapter-01/chapter-notes.md +- Core Thesis: Pending post-reading review. +- Key Concepts: Author credibility; maintaining systems; production evidence; information supplied to AI. +- Action Item: Pending post-reading review. + +### Running Threads +- The author frames long-term system maintenance—not merely initial code production—as the source of the book's practical perspective. +- The central claim to test is that the difference between consistent AI output and an expensive guess usually lies in the information supplied to the model. +- Distinguish evidence of the author's experience from evidence that the book's general claims are correct. +- Reader finished Chapter 1. Three active-recall questions are saved in /library/Context Engineering/Chapter-01/chapter-notes.md; responses are pending. + ## Your Best Year Ever — Michael Hyatt - **Status**: In Progress - **Current Position**: Chapter 2 of 15 read; active-recall review awaiting reader responses diff --git a/Spec Driven Design - EN_ From vibe-coding to software engineering (1).pdf b/Spec Driven Design - EN_ From vibe-coding to software engineering (1).pdf new file mode 100644 index 0000000..8097436 Binary files /dev/null and b/Spec Driven Design - EN_ From vibe-coding to software engineering (1).pdf differ diff --git a/library/Context Engineering/Chapter-01/chapter-notes.md b/library/Context Engineering/Chapter-01/chapter-notes.md new file mode 100644 index 0000000..c5bdb99 --- /dev/null +++ b/library/Context Engineering/Chapter-01/chapter-notes.md @@ -0,0 +1,34 @@ +# Context Engineering: Engineering Information for AI Systems — Chapter 01: About the Author +- **Date Created**: 2026-10-01 +- **Status**: In Progress + +--- + +## 1. Pre-Reading Briefing +- **Core Question**: What experience and evidence standard does J.C. Ködel present as the basis for teaching context engineering? +- **Key Points to Watch For**: + - The kinds of software systems the author has built and maintained. + - The distinction between producing code and sustaining a system over time. + - Why the author uses a long-running independently operated product as evidence of practical credibility. + - The claim that AI output quality depends heavily on the information supplied to the model. + - How the author distinguishes production experience, attribution, and unsupported theory. +- **Context & Thread from Prior Chapters**: This is the opening section, so there is no earlier argument to connect yet. Treat it as a statement of scope, credibility, and evidentiary standards rather than as proof of the book's central claims. + +--- + +## 2. Reading Review & Reflections +- **Prompt Questions**: + 1. Which parts of Ködel's background does he use to establish credibility, and what do those experiences suggest he values in software engineering? + 2. In your own words, what does he claim usually separates a consistent AI result from an expensive guess? + 3. What does the author's experience give you good reason to trust—and what does it not yet prove about the book's claims? +- **User Key Takeaways**: +- **Scaffolding & Feedback**: + +--- + +## 3. Chapter Synthesis +- **Core Thesis**: Pending post-reading review. +- **Key Concepts / Mental Models**: +- **Notable Arguments & Evidence**: +- **Updates to Prior Understanding**: +- **Weekly Action Item**: diff --git a/library/Context Engineering/book-structure.md b/library/Context Engineering/book-structure.md new file mode 100644 index 0000000..66688a8 --- /dev/null +++ b/library/Context Engineering/book-structure.md @@ -0,0 +1,47 @@ +# Context Engineering: Engineering Information for AI Systems + +- **Author**: J.C. Ködel +- **Format**: PDF +- **Length**: 371 pages +- **Source File**: /library/Context Engineering/source-file.pdf +- **Top-Level Sections**: 36 +- **Note**: Sections 1–2 are orientation/front matter; the main technical argument begins in Section 3. + +## Contents + +1. About the author +2. Map of the trilogy +3. How LLMs use context +4. Tokens and context windows +5. Memory and limits +6. The context cycle +7. Context rot: why large contexts degrade quality +8. Token economics: the real cost of bad context +9. Parametric calculation: cost of irrelevant context +10. Prompt engineering vs context engineering: why the prompt became a second-order variable +11. Specifications +12. Living documentation +13. ADRs +14. Conventions +15. Persistent context files +16. Project organization +17. Modularization +18. Context for brownfield projects +19. Context layers +20. Context packing +21. Context recovery +22. Context validation +23. Context compression +24. Context isolation +25. RAG vs direct context +26. MCP and tools as dynamic context +27. Context security and trust +28. Where to start +29. Development loops with AI +30. Measuring context: how to evaluate whether your context improves results +31. Principles applied: chat, IDE, terminal and CI +32. Teams: context as a repository asset +33. Preparing a project (from scratch and from a legacy system) +34. A complete AI-guided implementation +35. Post-mortem: where the context failed and how it was recovered +36. References diff --git a/library/Context Engineering/source-file.pdf b/library/Context Engineering/source-file.pdf new file mode 100644 index 0000000..9e50dc2 Binary files /dev/null and b/library/Context Engineering/source-file.pdf differ