rushour0//blog

Field notes · AI agents & a Game Boy Advance game studio

Building an agent engine
by shipping a game on it.

Five essays on AI agent orchestration, cost, and retrieval — what it actually takes to make an LLM agent cheaper and more reliable while shipping a 2D Game Boy Advance game studio on top of it. Written from the commit log offabri andludexel, an agent engine and the product that keeps breaking it.

5 posts · read in order or jump in

fabri the engine ludexel the game it ships a failure → becomes a guideline ← cheaper default makes it cheaper to run
The whole series in one diagram: the product breaks the engine, the engine gets cheaper, repeat.

Series

Building an agent engine by shipping a game

Five essays on AI agent orchestration, cost, and retrieval — building an AI agent framework (fabri) and shipping a 2D Game Boy Advance game studio (ludexel) on top of it.

01 / 05·build-in-public·2 days ago

I built the engine and the product at the same time — on purpose

Two repos at once: an AI agent framework and the Game Boy Advance game studio built on it. Notes on building an agent engine and shipping a 2D game in public — the product is the only honest test of the engine.

read →
02 / 05·agent-infra·2 days ago

Frozen prompts are the bug

A system prompt for an AI agent shouldn’t be hand-written and frozen — it should grow from the traces of what the agent actually did. Notes on prompt engineering and self-improving agent memory.

read →
03 / 05·cost / COGS·2 days ago

Orchestration is a cost decision, not a topology diagram

The interesting multi-agent orchestration question isn’t how agents talk to each other — it’s the cheapest model for each step, and how you stop an AI agent’s LLM cost from leaking.

read →
04 / 05·retrieval / IR·2 days ago

You can't improve retrieval you never measured

I built a self-improving RAG memory system for weeks on vibes, then finally built the eval. The first recall@k measurement showed two shipped retrieval features doing nothing.

read →
05 / 05·reflection·2 days ago

What building a second project taught me about the first

The fastest way I found to improve an AI agent wasn’t tweaking its prompt or code — it was building a real product, a 2D Game Boy Advance game studio, that actually needed it.

read →