A few years ago someone told me I’m good at documenting my workflows. Truth is, I just hate repeating myself. Funny enough, that’s exactly the mindset that works best with AI. Agents, skills, slash commands… they all run on clear processes. Feels like the right time in history to have that pet peeve.
As we shift from Prompt Engineering to Context Engineering, one of the things I find myself (and others) doing is working with LLMs to craft the right prompt first. My LLM Stack First, here’s my obligatory AI stack. Daily drivers: LLM Desktop Apps: ChatGPT and Claude LLM CLIs: Codex, Claude Code, Gemini, and more recently, Copilot CLI Windsurf: All the benefits of Visual Studio, which I use for editing and reviewing code. I still think its intelligent multiline autocomplete is unmatched. Weekly tools: ...