The AI Assistant
How it stays safe
All-or-nothing edits, automatic retries, and guardrails that mean the Assistant can never half-break your scene.
Open in the interactive manual →The interactive version has full-text search, a table of contents, and light/dark themes.
Handing an AI the keys to your scene sounds risky — so 3dCMS wraps it in guardrails that make the Assistant safe to trust.
- All-or-nothing edits. Every batch is validated before it's applied. If any single operation is invalid, the whole batch is rejected and your scene is left exactly as it was — never half-applied.
- It retries. When a batch is rejected, the Assistant is told what went wrong and gets a couple of automatic attempts to fix it.
- One Undo. The entire edit — however many objects it touched — collapses into a single Undo step. Don't like the result? One Ctrl+Z.
- Sanity guards. Nonsense transforms (a position that isn't three real numbers) are rejected outright, so objects can't be flung into the void or vanish.
- It targets objects by identity, never by guesswork, so it edits the thing you meant.
Imported & generated models recolor differently
Models that carry their own baked-in materials can't be repainted with a flat color — the Assistant tints them instead. If you ask to "make the imported statue blue," expect a tint, not a full repaint.
If something does go wrong on Anthropic's side (a bad key, a rate limit), the Assistant shows a plain-language message telling you what to check.
Spotted something off, or want a topic covered? Email buck.rackley@gmail.com.