Coding agents forget everything between sessions, and the bigger the codebase grows, the more they have to rediscover before they can do anything useful.

This article covers spec-driven development as a whole - why agents need specs, the frameworks worth starting with, and how my own setup evolved from homegrown commands to OpenSpec and beads.

Executing coding agents from the shell or your desktop executes commands with your user's privileges. Their own guardrails have come a long way, but a prompt injection can hide in many places - open-source packages, images with invisible text, which only the agent reads, harmful instructions inside searched pages, the list goes on.

This article covers the most basic setup of sandboxing a local agent for daily tasks inside a dev container.

How I researched, designed, coded and deployed my Astro blog in a single day - heavily assisted by AI tools.

My goal was to have a blog built in a way that I can write articles in markdown directly, without having to rely on a CMS. I wanted to have component architecture, like most React frameworks. I ended up with a site that is fast, beats the Lighthouse score, is SEO-friendly and is free to host.

Vibe coding is the new hype. Everybody is doing it, even non-technical people that have no clue about what happens under the hood. I was sceptical at first, but after adopting Claude Code, I'm entering the new now, all hands on deck.

This is a post about my AI-powered coding workflow with Claude Code, Copilot and ChatGPT at the end of 2025.