Dev Log

From the Workshop

Behind-the-scenes notes on building games, forging tools, and running a small studio that punches above its weight.

4 June 2026

How Pi Agents Build, Test, and Ship Game Code with Oracle-Backed Flows

We type a slash command, agents fan out through five oracle gates, the game-builder fixes 19 red tests while vision judges check the live game — and it all runs as one autonomous flow.

Read →
3 June 2026

How We Restyled Our Blog with Two Template Files and Zero Dependencies

We gave the Tinqs blog a visual refresh — gradient titles, dark code panels, date pills, amber accent bars. Two template files, one build step, zero external dependencies.

Read →
25 May 2026

What an Agent Harness Is and Why Game Dev Needs One

A raw AI model is stateless. An agent harness wraps around it and provides identity, memory, tools, context, and guardrails. Here's why game development needs its own.

Read →
25 May 2026

AI Art at Every Price Point: How We Generate Game Assets with fal.ai

We generate all visual assets for our game through fal.ai — concept art, icons, logos, trailer frames. Here's the 4-layer prompt pattern that actually works, and how we pick between 12 models spanning two orders of magnitude in cost.

Read →
25 May 2026

Fork, Don't Build: How We Modified Gitea, Pi, and Godot Instead of Starting from Scratch

Three forks, less than 0.5% code changed. Why modifying existing platforms beats building new ones — and how we turned Gitea into a game dev platform with 3D preview, AI agents, and LFS-first workflows.

Read →
25 May 2026

A Pre-Commit Agent That Guards Your Secrets for $0.001

Too many things to remember before hitting commit. Don't leak API keys. Don't reference classified codenames. Don't link to deleted repos. We built a two-layer pre-commit hook — regex + LLM — that catches all of it for $0.001.

Read →
22 May 2026

Streaming a 12km Archipelago in Godot 4

Godot has no built-in asset streaming. We built four layers to run a 12km archipelago with 9 islands, 155 vegetation types, and 2,000 crowd instances — on an RTX 3060.

Read →
18 May 2026

One Binary to Rule Them All: Our Studio CLI

Every machine in our studio runs the same Go binary. It knows who you are, what machine you're on, and what services are reachable. It takes screenshots, sends them to cloud vision, and runs health checks — in 100ms.

Read →
6 March 2026

How a 4-Person Studio Runs on AI Agents

We gave AI agents persistent identities, skill playbooks, and access to our entire knowledge base. Here's how four people ship like forty.

Read →