Spec Kit pilot — writing the spec before the code
As a non-programmer directing AI, can a 'spec-driven' workflow — write the spec first, then a plan, then tasks, then code — make what I build more deliberate and less improvised?
// Filter
Tagged: Systems
A creative studio run as a system of AI agents
As a non-programmer, can I run a whole creative studio as a coordinated system of AI agents — a main orchestrator that routes work to specialized sub-agents, each scoped to its own domain — instead of leaning on one general-purpose assistant?
When the research kills your favourite idea — designing a roster from data instead of taste
I was designing the character line-up for a miniatures campaign aimed at a specific fan community. I had a set of archetypes I liked and that fit the theme beautifully. Before sculpting anything, could I check whether the audience actually wanted them — and would I accept the answer if it said no?
Taking a 1993 strategy game apart to find out how it works
I keep borrowing mechanics from Ogre Battle: The March of the Black Queen for my own game design. But borrowing a mechanic you've only *felt* is guesswork. Could I reverse-engineer its systems properly — write them down as specs — and rebuild the first map to prove I actually understood them?
MANTICORE — the calendar layer nobody builds before the content plan
Every content calendar starts by asking 'what do we post?' — but that skips a step. What dates actually matter to *this* business, and can that question be answered systematically instead of by whoever happens to remember Black Friday?
MASSIMO — a design system builder, paused for the most useful reason
I already had a visual language for my own work. Could the same discipline be turned into something repeatable — a way to stand up a design system for any brand, and then produce real pieces against it instead of eyeballing every post?
LORD — strategy for live streamers, where the platform gives you nothing
Small streamers are told to 'post more clips' and 'be consistent'. But below a certain size the platform doesn't distribute you at all, so most advice is noise. What actually moves a channel that nobody is being shown?
The glossary — the real bottleneck in building with AI isn't the AI
I direct AI to build software without writing the code myself. So what is actually the limiting factor? I assumed it was the model's ability. It isn't — it's my ability to say precisely what I want in the vocabulary the work happens in.
From niche research to a validated ad: running a real Meta campaign with AI
Every other project in this log points the same method — research, plan, produce, verify — at games and 3D tools. Could it run a marketing engagement end to end? Not a mock-up: a real local business, a real audience, real videos, real money in Meta Ads Manager, and a measurable answer about which creative earns attention cheapest.
A playable XCOM-style demo in Godot, built without opening the editor
Two questions stacked on top of each other. Design: my tabletop universe needed a digital tactics demo, and I decided to borrow 97% of it from XCOM on purpose — grid, two actions, cover, line of sight, overwatch — so that the remaining 3% could be genuinely mine. Tooling: could an AI agent build that in a real game engine, Godot, without me ever having to open the editor to check its work?