Security & Data Handling

How SceneGen treats your code, your data, and your privacy.

The short version

SceneGen reads parts of your codebase to generate a video. Your code is never stored, never shared, and never used for AI training. Once your video is rendered, all code data is discarded.

What we read from your codebase

When you point SceneGen at a project, we scan for:

We do not read: .env files, credentials, secrets, private keys, database contents, user data, or anything in node_modules, .git, or build output directories.

What we send to the AI

A compact summary of your codebase — typically the first 200 lines of 10-18 key files — is sent to Anthropic's Claude API to generate your storyboard and scene components. This summary includes:

What Anthropic does with your data

We use Anthropic's commercial API, which has clear data handling commitments:

What we store

We do not store your source code, design tokens, or brand images after your video is rendered.

What we never do

Infrastructure

Questions?

If you have security concerns or questions about how we handle your data, reach out directly: eric@scenegen.dev