working_with_existing_code:start

Working with Existing Code

'Working With Existing Code' is about learning to see code the way AI sees it — as fragments, and without context. It's also about understanding how to provide clarity, boundaries, and intent that let AI act safely within 'an existing system'. This topic teaches us how to reveal just the right parts of the codebase, how to describe relationships that AI 'cannot infer', and how to collaborate with AI in a way that preserves structure, purpose, and architectural integrity.
Please sort A-Z for intended reading sequence.

01. Preface: This is a long topic, but easy to read
02. How AI Sees Code (and What It Cannot See)
03. Showing AI the Right Parts of the Code (and Only the Right Parts)
04. Temporary Hacks (Like !important) — How to Use Them Without Creating Noise
05. When AI Suggests a Refactor (How to Decide What to Accept)
06. Safe Refactoring — How to Guide AI Toward Minimal, Predictable Changes
07. Working With Legacy Code (How to Guide AI Through Older Patterns)
08. Working With Themes and Plugins (How to Keep AI Inside the Boundaries)
09. When AI Gets Lost (How to Reset, Re‑Anchor, and Regain Control)
10. When AI Misunderstands the System (How to Reveal the Missing Context)
11. When AI Misunderstands a Pattern (How to Correct the Shape and Preserve the Intent)
12. When AI Over‑Refactors (How to Restore Simplicity)
13. When AI Breaks the Architecture (How to Re‑Assert the System’s Rules)
14. When AI Invents Features (How to Prevent Hallucinated Behavior)
15. When AI Misreads Intent (How to Re‑Center the Goal)
16. When AI Over‑Explains (How to Bring the Work Back to Clarity)
17. When AI Misses the Edge Case (How to Reveal the Hidden Risk)
18. When AI Misjudges Priority (How to Keep the Work Aligned With What Matters)
19. When AI Overgeneralizes (How to Bring the Work Back to the Specific)
20. When AI Over‑Corrects (How to Keep the Work Stable and Minimal)
21. When AI Misreads the Audience (How to Match the Explanation to the Reader)
22. When AI Misses the Hidden Dependency (How to Reveal What the System Relies On)
23. When AI Invents a Convention (How to Keep the System Grounded in Reality)
24. When AI Over‑Explains the Obvious (How to Keep the Work Focused and Respectful of the Reader)
25. When AI Over‑Documents (How to Keep Comments Useful, Minimal, and Honest)
26. When AI Misreads the Level of Risk (How to Keep Changes Safe and Proportionate)
27. When AI Misreads the Cost of Change (How to Keep the Work Efficient and Sustainable)
28. When AI Misreads the Impact of a Change (How to Keep the Work Focused on What Actually Improves the System)
29. When AI Misreads the Stability of a Change (How to Keep the Work Future‑Proof and Maintainable)
30. When AI Misreads the Dependencies (How to Keep the Work Coherent Across the System)
31. When AI Misreads the Boundaries (How to Keep Components Separate and Responsibilities Clear)
32. When AI Misreads the Intent of the Code (How to Keep the Work Aligned With What the Code Is For)
33. When AI Misreads the Constraints (How to Keep the Work Within the Real Limits of the System)
34. When AI Misreads the History of the Code (How to Keep the Work Aligned With Why the Code Became What It Is)
35. When AI Misreads the Context of the Change (How to Keep the Work Aligned With the Situation Around It)
36. Closing — Working With Existing Code Is an Act of Stewardship

working_with_existing_code/start.txt · Last modified: 2026/05/19 09:21 by editor