Auto Review
Published Updated
What is Auto Review?
An automatic AI review of a queued prompt before approval, run on the configured review model (default GPT-5.6 Luna via Sivants subscription).
When enabled per complexity tier in Settings → Prompt Review, Auto Review evaluates a draft prompt for issues, missing context, or scope problems before you approve it. The default review model is GPT-5.6 Luna using Orbit's included subscription key, but you can configure other models with your own keys.
How it relates to Orbit
Orbit’s queue review controls decide when a prompt needs a human approval before execution. See Approval & Review for details.
When you would use it
Default behavior for medium-complexity prompts. Power users may disable Auto Review for routine work.
Common operations
- Catching prompt issues before queueing
- Routine sanity checks on medium-tier work
Related terms
Where this is taught
No learning path uses this term yet. Browse the Learning Atlas for guided sequences through related ideas.