AI Workflows
Reading an unfamiliar codebase with an LLM (a 4-step process)
Inheriting code is easier with an LLM if you ask the right questions in the right order. The 4-step process that surfaces the architecture in under an hour.
Honam Kang5 min
AI Workflows
AI Workflows
How to organize projects, prompts, and artifacts when you run multiple AI agents in parallel.
AI Workflows
Worktree, branch, or session: parallelism patterns for AI dev
Three different ways to keep parallel AI agents from stepping on each other. Each has a place; getting the choice right per task saves real conflicts.
Honam Kang5 min
AI Workflows
A 4-pane workflow for LLM research: source, references, scratchpad, output
When you're using an LLM to read papers, summarize sources, and write a synthesis, four file-manager panes beat 14 browser tabs. Here's how to wire it up.
Honam Kang4 min
AI Workflows
How to write a CLAUDE.md that actually helps the agent
CLAUDE.md is the most-undervalued AI productivity tool. A good one saves hours per week; a generic one is dead weight. Here's what makes the difference.
Honam Kang4 min
AI Workflows
Organize your AI prompts on disk: a flat library, version-controlled, reusable
Stop pasting the same instructions into every chat. Here's a battle-tested layout for a personal prompt library that you can grep, version-control, and share between Claude Code, Cursor, and Codex.
Honam Kang4 min
AI Workflows
Setting up a parallel agent fleet on macOS (5+ sessions, no chaos)
Running five Claude Code sessions on one Mac without losing track is a workflow problem, not an AI problem. Here's the layout that survives daily use.
Honam Kang5 min
AI Workflows
How to organize Claude Code projects on macOS (a workflow that survives 10 sessions)
A directory layout, naming convention, and pane-routing strategy for running multiple Claude Code sessions on macOS without losing your place.
Honam Kang5 min