How to engineer an AI harness for game development
The author shares ideas from a 45-minute talk titled “Your Game Is A Harness” at Indie Rodeo in Calgary, stressing that the blog post was written by hand rather than transcribed from the slides. The article argues for using LLMs in real day-to-day game development instead of one-shot demos, recommending exact save/load and deterministic state from the start plus a data-oriented, binary-isolated, no-compile architecture so an agentic loop can run in seconds. The author says any game can serve as its own harness, but notes in a postscript that a small project he is shipping uses none of these techniques, which he sees as suited to larger projects.
It sketches a concrete workflow for making a game codebase legible and testable to LLM agents, though the claimed seconds-long iteration loop is the author's personal, unmeasured experience.

I gave a 45 minute presentation entitled“Your Game Is A Harness” as part of Indie Rodeo in Calgary on 9/12/26. After speaking with a lot of people after my talk, I thought it would be good to more broadly share the ideas I presented there in a form that could be enjoyed by people beyond just those who attended the conference.
Also, because I talk about AI a lot on this blog, people assume I use AI to write. This is not true! Everything below is 100% human authored, with me writing the post with basically only the slides I presented as a reference (this is not a transcription). As much as I enjoy using AI to write code and tools, I get a similar enjoyment out of writing“the old way”, especially as I have no reason to try and make any part of this process more efficient.
Some source content is omitted. Continue reading on the original site.