How my AI workflow evolved from prompts to workflow

About six months ago, my AI workflow was already useful. I had reusable commands. I had predefined templates. I had a decent setup in Cursor and later Claude Code and Codex. It was enough to make AI generate code faster, help me plan, and reduce some repeated prompting. That was already a big step up … Continue reading How my AI workflow evolved from prompts to workflow

Tokens, Context Windows, and why your AI agent feels stupid sometimes

When an AI coding agent forgot a constraint, drifted halfway through a task, or confidently invented things that never existed, some of our first reactions are that "this model is not good enough". After using Cursor, Claude Code, and other AI coding agents daily for a long time, I changed my mind. When a capable … Continue reading Tokens, Context Windows, and why your AI agent feels stupid sometimes

AI Coding Agents Explained: Rules, Commands, Skills, MCP, Hooks

If you are an engineer today, the challenge is no longer whether AI can help you write code. The challenge is the flood of tools and concepts. Every few weeks, there is something new. Agents, rules, skills, sub-agents, MCP, hooks. Each introduces its own vocabulary, and most explanations jump straight into features without explaining why … Continue reading AI Coding Agents Explained: Rules, Commands, Skills, MCP, Hooks

Claude Code vs Cursor

I’ve seen a lot of Cursor vs Claude Code comparisons recently. Most of them try to answer a simple question: which one writes better code? https://twitter.com/codeaholicguy/status/2006021401212256626 After using both tools daily, I think that question misses the point. I don’t see a meaningful difference in code quality between Cursor and Claude Code anymore. Once you … Continue reading Claude Code vs Cursor

Prompts are becoming Code, but we still treat them like Strings

Prompts used to be just text. You wrote a few sentences, pasted them into a chat box, tweaked the wording, and moved on. If the output was not good, you tried again. Nothing else depended on it. The cost of getting it wrong was close to zero. That phase did not last long. In The … Continue reading Prompts are becoming Code, but we still treat them like Strings