SceneFoundry — a purpose-built game studio for people & AI
When I started building the game content for Reveal Haven, I found myself switching between a multitude of tools — Gemini and OpenAI studios, Photoshop, scripts, audio editors, and the game engine. That put barriers in front of the creative process, and it wasn’t something I could reasonably teach the artist I hired to build scenes.
So I turned to AI to build a custom studio for the game, named SceneFoundry — and was amazed at the results. It keeps a person at the centre on purpose. Whether a map makes someone want to explore it, whether an object is challenging to find, whether the audio captures the atmosphere of a scene — it all comes together in one place.
“It’s fascinating to me to think about AI as a potential new artistic medium in the same way that the camera was a new artistic medium.”
Building a consistent world
The hallmark of a great game is a consistent style and aesthetic, which requires instructing the AI to be consistent when generating scenes that are part of the same adventure. So before a single scene exists, the author writes the adventure’s blueprint — the world it’s set in, the style it’s drawn in, and the voice its objects speak in. That adventure-level meta-prompt is the throughline: it’s what keeps twenty-three scenes of one world looking, and reading, like one world. People bring the taste and the intent; the models hold the line.
- WorldAn authoring guide the models treat as ground truth — never shown to players.
- StyleA flat-2D-illustrated switch, or photoreal — set per adventure.
- VoiceDescriptions grounded in real-world fact, or purely in this world’s lore.
You describe it. The model drafts it. You choose.
A scene isn’t typed into a prompt box and accepted. It’s a short back-and-forth — the human sets direction, the model does the heavy lifting, and the human keeps the final say at every gate.
That loop — direct → generate → judge — repeats for every object, cutout, description and sound in the world. The AI never ships anything a person didn’t choose.
Find an object, and it has to leave something behind.
The game ships each scene as a clean background plate with object cutouts composited on top. Tap a hidden object and its cutout fades away — revealing the plate beneath. So the tool has to know what was always behind every findable, and paint it. That inpainted patch is the quiet, load-bearing problem SceneFoundry exists to solve — at hundreds of objects per adventure.
Drag the handle and watch it happen: the Weaver Bird lifted out, the empty nest seamlessly filled — then a person confirming the reveal actually looks right. Being able to see it is what makes that call possible. And from there one click carries the plate, the cutouts and their coordinates into the game engine and on through publish — nothing to export, re-crop or hand-wire between tools, which leaves the person free to think about the experience.
The model’s first pass, a person’s finishing tools.
Infill is one move in a much larger toolkit. Every extracted object opens into a full editor: a prompt you can rewrite and regenerate, alongside pixel tools to clean the cutout by hand — no round-trip to Photoshop. The AI gets you 90% of the way; the human tools close the last 10% that makes an asset actually shippable.
And the words, in bulk — then curated.
Display names, lore descriptions and thumbnails generate as mass actions across every object at once — then a human reads down the review table and approves, edits, or regenerates each one. Volume from the machine, judgement from the person.
No single model is best at everything — so none is hard-wired.
Each job routes to the provider that’s currently best at it, through one facade and a queued lane per model. Swapping is a per-request decision, not a rewrite.
| Job | Provider | Model |
|---|---|---|
| Segmentation | Replicate | yodagg / sam3-image-seg |
| Image generation | Gemini OpenAI | gemini-3-pro-image · gpt-image-2 |
| Inpaint & removal | Gemini OpenAI | gemini-3.1-flash-image · gpt-image-2 |
| Descriptions & metadata | Gemini | gemini-3-flash-preview |
| Sound & ambience | ElevenLabs | eleven_text_to_sound_v2 |
| Enhance / upscale | Krea | Reimagine |
An adventure builder — end to end.
SceneFoundry doesn’t stop at scenes. One tool generates the illustrated world map and places its locations, forges the achievement tokens and title graphics, writes and generates the ambient sound, and holds every scene with its objects. A single author takes an adventure from blank to shippable.
Not a demo — an instrumented tool in daily use.
SceneFoundry meters itself. The action counts say which motion an author repeats hundreds of times a week, and that is where the next hour of tool-building goes. Friction you can see is friction you can remove; the tool improves in the places the telemetry says it should.
The authoring tool is larger than the game it feeds — its backend alone is two-thirds the size of the whole web game.