<metaname="description"content="Dev logs, behind-the-scenes, and lessons learned from building games, tools, and platform infrastructure at Tinqs Studio.">
<h1class="blog-header__title">From the Workshop</h1>
<pclass="blog-header__subtitle">Behind-the-scenes notes on building games, forging tools, and running a small studio that punches above its weight.</p>
<pclass="blog-card__excerpt">A flow spawns, 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.</p>
<h2class="blog-card__title">Why Voice Is the Missing Input for Game Development</h2>
<pclass="blog-card__excerpt">Speaking a bug while looking at the screen beats typing it from memory ten minutes later. Here's how voice-to-agent pipelines work, why game dev is the ideal use case, and what changes when you stop typing bug reports.</p>
<h2class="blog-card__title">Live Ozan Radio: A Personal AI Station in Cursor</h2>
<pclass="blog-card__excerpt">I wanted a radio that never plays catalog music — only fresh AI compositions shaped by my taste. Here's the stack, the player, and how I DJ every generated track with metadata.</p>
<h2class="blog-card__title">How We Restyled Our Blog with Two Template Files and Zero Dependencies</h2>
<pclass="blog-card__excerpt">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.</p>
<h2class="blog-card__title">What an Agent Harness Is and Why Game Dev Needs One</h2>
<pclass="blog-card__excerpt">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.</p>
<h2class="blog-card__title">AI Art at Every Price Point: How We Generate Game Assets with fal.ai</h2>
<pclass="blog-card__excerpt">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.</p>
<h2class="blog-card__title">Fork, Don't Build: How We Modified Gitea, Pi, and Godot Instead of Starting from Scratch</h2>
<pclass="blog-card__excerpt">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.</p>
<pclass="blog-card__excerpt">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.</p>
<pclass="blog-card__excerpt">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.</p>
<h2class="blog-card__title">One Binary to Rule Them All: Our Studio CLI</h2>
<pclass="blog-card__excerpt">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.</p>
<h2class="blog-card__title">How a 4-Person Studio Runs on AI Agents</h2>
<pclass="blog-card__excerpt">We gave AI agents persistent identities, skill playbooks, and access to our entire knowledge base. Here's how four people ship like forty.</p>
