Blog

Script from an LLM, custom skills, HyperFrames and storyboards.

How I choose between Claude Code and Codex when making games.

Voice in and out, asking for reports, and holodecks as the future of entertainment.

Iterations with manual or automated gates, with proper planning.

Spotting when something should be a skill.

Why images and references do so much in AI game dev.

Planning with Fable / Astra, executing with Opus or similar.

Why I prototype games in Godot.

Generating models with Tripo3D, then cleaning them up with Codex and the Blender MCP.

Using Gemini and other web LLMs to come up with game ideas.

Configurations are easy and cheap now, so design decisions can be different.

Languages don't matter anymore. Asking 'do you know Java?' stopped mattering. The world changed, and a lot of us haven't caught up yet. It takes change to see change.

For the first time, humans can actually multitask — how to do it well.

How I actually build games day to day with AI in the loop.

Setting up vibe coding with voice — the software, the mic, and getting off the keyboard.

isPrime on a whiteboard and 'name every primitive data type' measured memorization — a signal that died the day every candidate got an AI pair. Test judgment, not recall.

Every industry solved how to look at its data — from subway maps to blueprints. We're still staring at text files.

Wiring sensors and microcontrollers into my stack to watch, alert on, and automate my applications in the real world.

A menu bar is the cheapest mission control you'll ever build — glance at every agent, build, and deploy, and control them without leaving your screen.

A field guide to delegating with /goal agents — when a goal beats a one-off prompt, and how to dial thinking effort up or down for the job.

Practical ways to level up your agents — memory, feedback loops, and the habits that compound.

Running retrospectives with your agents — why reviewing what went wrong is worth the time.

My everyday kit of custom skills and slash commands — what each one does and why it earns its keep.

The questions I ask before writing a single line for something new.

Why I write plans in HTML now, and how it makes them easier to design and execute.

Dynamic agent workflows, agent teams, and a caffeinated computer — when to run them overnight and how.

AI doesn't change your skills — it amplifies the ones you already have.

Why I'd rather spend an afternoon building it than another month subscribing.

Why you should make games — and how AI lowers the barrier to start.

How interactive, AI-generated games are quietly becoming the future of how we learn.

How I use an ESP32 and a local model to track the birds in my backyard.

Why rewriting beats fixing — especially with LLMs.

Tests, automation, test dashboards, and a vibe kanban — the missing discipline in AI-assisted coding.

Give your AI eyes, a finish line, and the right tools — the essential toolkit for AI-assisted development.

How an AI coding assistant helped me build a plant watering system.

The mobile-first coding workflow that lets me ship from anywhere.

How to orchestrate multiple AI agents for complex development tasks.

How I use Claude/Cursor to configure safety rules that prevent destructive commands.

Why I write custom scripts for repetitive tasks instead of burning through LLM context.