Development
8 articles about development.
Build vs Call Another Agent
When to build your own agent capability versus integrating with an external agent - the 3x/day rule and why integration overhead is always higher than expected.
Debugging Unexpected AI Agent Behavior: A Practical Playbook
When your AI agent does something you did not ask for - or does the right thing the wrong way - here is how to diagnose it, reproduce it, and decide whether to fix it or accept it.
Git Worktrees Are Non-Negotiable for Parallel AI Agent Teams
Running multiple AI coding agents in Claude Code without git worktrees is asking for merge conflicts. Here's why worktrees are the foundation for agent team
Vibecoded App with Claude Code
Vibecoding with CLAUDE.md architecture rules turns Claude Code from a code generator into a system-aware development partner. Here is how the approach works.
Questions That Won't Sit Still - Unsolved Problems Driving AI Agent Iteration
The hardest questions in AI agent development are the ones that keep coming back. Explore the unsolved problems that drive continuous iteration in desktop
Recompiling Frustration Into Useful Output - The Emotional Cycle of Agent Development
Debugging AI agents is an emotional process. Learn how to channel frustration into productive debugging output and better agent development practices.
Using Claude Code Hooks for Native macOS Swift Development
How Claude Code hooks transformed native macOS Swift development. Auto-format on save, run tests before commit, validate builds - the workflow game changer.
VS Code Claude Extension vs Terminal with Ollama - Why the Terminal Route Wins
The VS Code Claude extension is locked to Anthropic's API. Running Claude Code in the terminal with Ollama gives you local models, more control, and zero