What we need from your engine
What a studio has to expose in the real game before Playthrough can start: a legal-action door in the engine, why we do not start with pixels and clicks, and what that interface opens later.
Read moreIdeas, evidence, and field notes
Ideas shaped by how worlds work.
Research, articles, case studies, and coverage from the systems we build and the worlds that inform them.
The same agents through the life of a game
This post explains how agents that play your game like people can help design and QA from first ideas through the years after launch, and how those same agents can later become language modes, AI players in matchmaking, and a simpler way for more people to play a hard game.
Read more
Patch day still runs on stories
After a live patch, clips and charts arrive first. They are useful, and they are the wrong kind of evidence for most balance calls. You need matches played in the real game that a designer can open again.
Read morePort the intent. Not the UI.
Hardcore games often look niche because the interface filters who can play them. Language control keeps the hard game intact and changes who can reach it, on which device, and how studios should underwrite that audience.
Read more
When agents finish the work, not just the answer
SpaceXAI's Grok Bot early beta is aimed at agents that finish multi-step work inside the software people already use. Our take: it is the best mass agentic workflow experience we have seen yet, and it puts Grok firmly in the running.
Read more
Owning the model when frontier APIs are not enough
Frontier APIs are a fast start. At volume, latency and proprietary data push enterprises and game studios toward open weights, distillation, and models they can actually own.
Read moreGenerate the material, not just the map
Most generative 3D tools stop at texture maps. Production still needs shaders, wiring, and behavior. Generating the material means landing something editable and engine-native.
Read moreBuild the sim, reuse the intelligence
Eval bots and player-facing AI often diverge into separate stacks that cannot transfer learning. A shared legal-action loop over the real engine lets simulation and player modes improve together.
Read more