What I test and learn about AI coding tools such as Claude Code, AI agents and MCP, and web development with PHP.
Three articles in reading order: from setting up Claude Code in PhpStorm to letting it work unattended.
Installing the CLI and the plugin, plus four habits for daily work.
Keeping the context clean, planning first and letting Claude check its own work.
Letting it run unattended for longer, with auto mode, the Ralph loop and tmux.
Which AI model can you run locally on an ordinary 16 GB laptop? Qwen3.5 and Gemma 4 compared, with measured speeds, a step-by-step Ollama setup, tasks to start with and the two settings that make the most difference.
Mistral Large 4 is the first European open-weight model with a trillion parameters. What Mistral's figures do and do not say, what it costs, what hardware you need and why the licence is the biggest open question.
Jev does not write text; it answers multiple-choice questions with a probability for each answer. The principle in plain language, with PHP examples you can copy, up to Claude and Jev working together.
Several AI agents passing work to each other: when it pays off, why research says it fails so often, what A2A and MCP do and do not cover, and what a good handoff looks like in PHP.
Jev by TypeSafe AI writes no text: it picks from your list and attaches probabilities. What independent tests measure, what a decision costs, and when plain code or a trained classifier is the better choice.
MCP is the open standard that lets AI applications discover and use tools and data. How it works, what the July 2026 specification changes and why securing integrations is still your job.
Most Claude Code tips are about hidden commands. The real difference comes from three things: keeping context clean, planning first and making Claude check its own work.
Forrest Chang turned Karpathy's criticism of coding agents into four behaviour rules in a single CLAUDE.md. What they do, why they help and where they stop.
Agent = model + harness. What an agent harness is, why the same model can score much higher in a different harness, and how guides and sensors steer an agent.