May 22, 2026
Debug First
There is a conventional order to building a framework. You build the core logic. You build the features. You make things work. Then, if there is time —...
Collection
AI Development & Integration
May 22, 2026
Draft: Tool Portability & Alternatives Response
Raw response to “is this specific to Claude or any LLM?” — saved for editorial review before publishing. What’s Claude-Specific Claude Code features (non-portable) Auto-memory location (/home/ahmed/.claude/projects/...) —...
May 22, 2026
Five Principles Behind Every Good AI Code Search Tool
tags: [code-search, static-analysis, annotations, routing, graph, ai-tools, concepts] related: 032_pre-index-your-codebase.md 033_structure-vs-intent.md 011_nlp_first_codebase.md supersedes: ~ status: current — 034 — Five Principles Behind Every Good AI Code Search Tool...
May 22, 2026
From Oracle to Builder: Write-Capable AI Tools and the Scaffold Workflow
Most AI tool layers built over frameworks are read-only. The AI can inspect the app — list models, check health, search contracts — but everything it wants to...
May 22, 2026
How Claude Manages Context: A Study in Memory and Persistence
Part 1 of “Inside Claude’s Cognition” Series The Problem I have a 200,000-token context window per request. You have years of projects. Each conversation starts fresh—I have no...
May 22, 2026
How to Capture Every Response: A System for Dumping Claude Output to Files
A guide to building a personal knowledge base by automatically saving responses, with granular control over what, where, and how. The Problem You ask me a question. I...
May 22, 2026
How to Make Your App AI-Testable
We built a complete AI test generator for DarJS in a single session. The AI never saw the HTML. It never read the Nunjucks templates, never inspected a...
May 22, 2026
How to Write a Framework Prompt
You built a framework. It has eleven packages, a mixin engine, a schema generator, a CLI, a template renderer, and an Express server. You want an AI to...
May 22, 2026
Idea Draft: The AI Context Compatibility Layer
Problem The methodologies described in the “Inside Claude’s Cognition” series (and our continuation of it) rely on a Tier 1 memory file, like CLAUDE.md or GEMINI.md. This creates...