void
wire
labs
Posts
Projects
About
categories · development
Development
2026
04-01
The Words I Don't Use
ai
agents
2025
08-07
Momentum: A Workflow That Helped Me Build
Packaging six months of workflow iteration into momentum - a Claude Code workflow that actually ships by treating AI as a compiler for operator expertise.
claude-code
workflow
07-30
The Real Cost of Claude Code Subagents
After burning through tokens with subagents, I learned when they're worth it and when custom commands work better.
ai
claude-code
07-24
F.O.C.U.S.
A meditation on constraint as capability
ai
llm
07-18
Don't Let LLMs Run the Show
Why LLMs excel at building software but struggle when put in control of runtime decisions and execution flow.
ai
development
07-10
How I Made Claude Code Actually Ship Software: A Systematic Workflow That Works
Building a systematic Claude Code workflow with commands, quality gates, and evidence-based completion that consistently ships working software.
claude-code
workflow
07-09
Force Your LLM to Spike
How forcing LLMs to perform research spikes before implementation can induce engineering behavior instead of just coding.
engineering
llm
07-04
Building My First Claude Code Hook: Closing the Hope and Pray Gap
How I discovered that the missing piece in my Claude Code + Desktop workflow wasn't better context management—it was finally having guardrails that actually know my standards.
claude-code
hooks
06-27
Claudex: From Ad-Hoc Context Creation to Repeatable Generation
Building on the three-layer memory system to eliminate the constant re-explaining of development preferences.
ai
development
06-18
The Interview Pattern: Why AI Should Ask Before It Acts
A short exploration of why letting AI interview you before implementation leads to better outcomes than discovering problems after the fact.
ai
development
06-10
Beyond Prompting: Why LLMs Break Down on Well-Architected Code and How Composition Saves Development
How we discovered that LLM limitations reveal fundamental truths about software architecture in the AI era
ai
development
06-09
The Architecture of Laziness: Why LLMs Are Fundamentally Designed to Cut Corners
AI-assisted development tools consistently cut corners on complex work. The problem isn't training or prompt engineering—it's architectural.
ai
development
2024
11-26
Sayable: Because AI Text Should Sound Good Too
A quick experiment in making AI output more TTS-friendly
ai
python