Skip to Oxygen content

Knowledge workers7 min read

Cloud AI: What Actually Leaves Your Workspace

“Private AI” is meaningless if you cannot say what stays and what leaves. Oxygen's split is deliberate: files and databases live in your cloud workspace. The main thing that leaves is model context for the LLM calls you choose to make.

What stays in the workspace

  • Organization corpus uploads in your cloud workspace.
  • Graph and vector stores used for document/CSV intelligence.
  • Hosted sandbox environment, packages, and project workspaces.
  • Editors, scripts, and in-app browser session clutter (no history/bookmarks theater).

What can leave

When you use a hosted model, prompts and the context assembled for that turn go to the model gateway you enable. That is the intentional egress path — metering and BYOK exist so finance/IT can reason about it. It is not the same as pasting a client folder into a consumer chatbot with training ambiguity.

Why the workspace matters

The studio runs in the browser against hosted workspaces and sandboxes. Org uploads live under your account and organization — closer to “a private studio you sign into” than “a mystery consumer chat product.”

Practical habits

  1. Prefer corpus/workspace workflows over copy-paste into random web UIs.
  2. Use BYOK on paid plans when keys must stay under your control.
  3. Minimize PII in analytics uploads (especially HR).
  4. Verify numbers and client-facing language before send.

FAQ

Do my files get trained into a public model?
Oxygen keeps corpus files in your workspace. Hosted LLM providers’ training policies depend on the gateway you enable — prefer BYOK and enterprise terms when that matters.
Do I need to install anything?
No. Open Creator Studio in the browser. Hosted model calls need network. Exact provider options depend on how you configure your plan.