Six projects across consumer apps, regulated health, and brand film. Every performer and scene is AI-generated — no shoot, no talent releases, no location. Every product shot is real app footage or a real store listing, never generated UI, because image models render on-screen text as gibberish. Claim language is reviewed before the script locks.
Method
Generated performers, real product. Every person and scene in this work is AI-generated — there is no filmed footage of real people anywhere in it. That takes casting, scheduling, talent releases and location out of the budget, and it means a persona can be recast in an afternoon instead of a reshoot.
The product itself is never generated. Image models render on-screen text as gibberish, so the app is always a real screen recording, a real store listing, real screenshots, or a live capture of the web app at a phone viewport. Generated people over a real interface is the whole method — and getting that boundary wrong is the single most common reason a finished video gets thrown away.
Claims reviewed before the script locks. On health, financial or regulated products, restricted language is identified first, and disclaimers are built into editable safe zones so wording can change without a re-render.
Every deliverable is reproducible. Briefs, prompts, source media and the assembly spec are retained together, so any cut can be rebuilt or revised months later without starting over.
Anyone can now generate a video. The difference is being handed the build that regenerates it, being able to prove the words are the words you approved, and being able to say why a pause is 6.20 seconds instead of 0.54.
