Launch Directory/AI & ML/Startup Launch
Startup Launch

Startup Launch · Launch Video Breakdown: Hook, Pacing & Motion Design

Gemini 4 Argon is now globally available. Built to solve your hardest problems from start to finish, the model brings frontier capabilities across coding, enterprise workflows, and cyber defense. htt

AI & MLProductionOctober 13, 2026@GoogleDeepMind
0:00 · The Hook · Introduction to the 3D Temple Build
0:00 / 0:00

Scene-by-scene timeline & spoken transcript

  1. The Hook

    Introduction to the 3D Temple Build

    “Hi, I'm George, a creative producer on the Gemini prototyping team at Google DeepMind. So, I built this 3D model of a Japanese temple complex in Blender using Gemini 4 Argon in Antigravity with a multi-agentic looping workflow based on a single prompt.”

    On screen
    George Kenwright Creative Producer Google DeepMind Built in Blender using Gemini 4 Argon
    Camera
    Split screen talking head alongside dynamic orbit shots of the 3D temple.
    Motion
    Side-by-side PIP layout transitioning into full-frame architectural showcase.
  2. Problem Agitation

    Why 3D Tests Model Intelligence

    “3D builds are a great way of testing a model's capabilities, particularly in areas like coding and world understanding. One, because building a 3D model is a technically complex programming task. Two, because it's immediately apparent if something is wrong with a 3D model, you can verify it instantly.”

    On screen
    Built in Blender using Gemini 4 Argon
    Camera
    Medium shot of speaker cutting to wireframe mesh turntable in Blender viewport.
    Motion
    Viewport flythrough showing complex wireframe geometry.
  3. Feature Teaser

    Model Progression Across Generations

    “We started using pagodas as a subject for 3D builds last year. It's useful to have a consistent subject so you can really kind of track the advancement in the models. But with Gemini 4 Argon, we wanted to take it a step further, building a photorealistic 3D model in Blender via a headless CLI.”

    On screen
    Gemini 2.5 Flash Gemini 2.5 Pro Gemini 2.5 Deep Think Built in Blender using Gemini 4 Argon
    Camera
    Frontal card view showing generational progression, panning to full 3D render.
    Motion
    UI comparison card animations with smooth easing.
  4. Product Reveal

    Prompt Architecture and Skill Specification

    “So this build was technically generated from a single prompt, but it was a little more complex than just build me a pagoda. It references a skill that we developed for building large, coherent 3D builds. A skill is essentially documentation that you give the model, in this case, via Antigravity. The prompt then asks Gemini to call a tool to create architectural blueprints for the building. The prompt then goes on to prompt Nano Banana to generate images based on those blueprint images. Those Nano Banana images, there are four of them and they're very important because they serve as references for the main part of the build, which is a multi-agentic adversarial loop.”

    On screen
    Built in Blender using Gemini 4 Argon SKILL.md Antigravity
    Camera
    Close-up screen capture scrolling technical documentation and CAD schematics.
    Motion
    Text highlight overlays, schematic pan/zoom, and reference comparison cards.
  5. Product Reveal

    Multi-Agent Orchestration & Refinement

    “Finally, the prompt divides work between different agents with an orchestrator agent overseeing everything. In this case, we can see how Gemini 4 Argon has divided them in Antigravity, all overseen by the orchestrator and adversarial critic. And we're rendering images within Blender, which are compared against those idealized Nano Banana images.”

    On screen
    Master Orchestrator & Adversarial Critic (Gemini 4 Argon) Pagoda & Roofline Specialist Tokyo Joinery & Cloister Specialist Threshold & Botanical Specialist Kondo Sanctuary & Altar Specialist Nano Banana Reference Images -> Final Angles from Blender
    Camera
    Screen capture of multi-agent UI followed by 3D viewport camera rig view.
    Motion
    Agent dashboard card transition, side-by-side A/B render comparison.
  6. Call to Action

    Final Renders and Model Sign-off

    “The next morning, came back and saw the results that we're seeing now. These were just images, so I asked the model to render some animations in Blender, and then also to procedurally generate some bell sounds and ambient sound effects to give it a little bit more atmosphere. One of my favorite things about working with these models is when you discover some new capability where the output seems almost impossible. And this sort of thing now is possible because of models like Gemini 4 Argon in Antigravity.”

    On screen
    Built in Blender using Gemini 4 Argon Gemini 4 Argon
    Camera
    Contact sheet grid zoom to cinematic beauty passes, concluding with logo card.
    Motion
    20-camera grid mosaic fade, cinematic slow panning, clean text reveal.

Related AI & ML Product Launches

Explore all AI & ML launches →
Tauvus
Hook 8.821.1M
TauvusAI & ML

Introducing Griffin, the first AI to pass the video Turing test

@tavus
Fish Audio
Hook 9.612.9M
Fish AudioAI & ML

The most emotive and controllable TTS model

@FishAudio
OpenAI
Hook 9.28.4M
OpenAIAI & ML

Always-on agents built to handle everything

@OpenAIDevs