Use Gemini with VVavy without adding a paid backend API

How the Gemini workflow works today

The clean path for VVavy is not a server that calls Gemini. It is a client-side handoff. Open VVavy, choose a custom visual workflow, copy the prompt, use Gemini in your own browser session, and paste the finished file back into VVavy.

1. Open VVavy and enter Custom Visuals.
2. Choose Create New Visual or Integrate Existing Visual.
3. Use Open Gemini or Copy prompt inside the editor.
4. Let Gemini return one final VVavy-ready JavaScript file.
5. Paste that file into VVavy, preview it live, and save it if it works.

Machine-readable resources Gemini can use

VVavy already publishes the key files an AI assistant or agent needs to stay on the current runtime contract.

• /llms.txt for a high-level product and workflow summary.
• /custom-visual-handoff.txt for compact AI fetches, and /custom-visual-schema.json as the readable JSON schema.
• /prompts/client-create-visual-create.md for a brand-new visual.
• /prompts/client-create-visual-integrate.md for adapting existing code or shaders.
• /visuals.json for the built-in visual catalog.

For deeper Gemini or agent workflows

If you want a more tool-like setup later, VVavy's current machine-readable surfaces are the right base layer. A Gemini-facing extension, agent, or local tooling layer can point at the same prompt files, compact handoff, readable schema, and visual metadata that the browser flow already uses.

That keeps the public contract simple: VVavy owns the visual runtime and resource files, while Gemini owns the generation step in the user's environment.