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
Author: codeaholicguy
software engineer, team lead at #kobiton, blogger at @codeaholicguy
I use AI DevKit to develop AI DevKit features
I built AI DevKit because I wanted a workflow that makes AI coding feel less random and more efficient. But I also know from experience that AI looks great when you demo it. The problem only surfaces when you rely on them to ship something non-trivial. I made a rule for myself. I would use … Continue reading I use AI DevKit to develop AI DevKit features
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
The Illusion of Output
AI makes it easy to produce output. You can generate code, designs, marketing ideas, user flows, or even a prototype in a few minutes. It looks impressive on the surface. It also creates a trap. People start to believe output means productivity. It does not. Output is cheap now. Anyone can create something. The real … Continue reading The Illusion of Output
Cursor 2.0 and Composer Model
Released on October 29, 2025, Cursor 2.0 is a major update to the AI-driven code editor that promises a new multi-agent interface and the debut of Cursor’s own coding model, Composer. As someone who uses Cursor every day, I couldn’t wait to try out the new 2.0 release. I spent some time exploring what’s new. … Continue reading Cursor 2.0 and Composer Model
A retrospective on AWS outage 2025
It started when we discovered that some of our build processes were unable to run due to failures in Docker. My first thought was the usual: “Is it us?”. I checked Docker health and found an incident from their side. Two minutes later, Twitter/X confirmed it wasn’t just us. AWS was having a bad day, and … Continue reading A retrospective on AWS outage 2025
My Engineering Workflow in CursorAI
Every Software Engineer follows a similar rhythm: Understand requirement → Design → Plan → Implement → Review → Test → Deploy → Monitor. That hasn’t changed for a long time. When AI is involved in the workflow, what’s changed is the speed. I also mentioned this in my FREE eBook about adapting AI in Software … Continue reading My Engineering Workflow in CursorAI
How to Create a ChatGPT App Using MCP (Model Context Protocol) Step by Step
OpenAI just announced the Apps SDK during OpenAI DevDay 2025. It quietly introduced something important, transforming ChatGPT from a Chat app to an App Platform. I wanted to understand how this works in practice, so I decided to build something small: a to-do app (because, well, this is something you build when you learn something … Continue reading How to Create a ChatGPT App Using MCP (Model Context Protocol) Step by Step
Testing Claude Sonnet 4.5, GPT-5 Codex, and Grok Code Fast 1 in Cursor: Which model fits best for development?
It has only been a few days since Anthropic announced their new model Claude Sonnet 4.5, and I wanted to see for myself if the hype matches reality. Instead of reading benchmarks, I opened Cursor and ran some coding tests to feel it as an end user. My goal with this test wasn’t to cover … Continue reading Testing Claude Sonnet 4.5, GPT-5 Codex, and Grok Code Fast 1 in Cursor: Which model fits best for development?
Codeaholicguy 