Creative QA

Use When

• Record human-in-the-loop quality judgments for generated images, voice takes, video renders, and final exports.
• Use after a person has reviewed an asset and you need structured verdicts, reasons, issue categories, blame stage, proposed action, and rerun guidance.

Do Not Use When

• No human verdict exists yet.
• The user wants autonomous AI approval.
• The task is prompt critique before generation; use preflight or prompt QA instead.

Required Input

• Human reviewer verdict and reasons.
• Target object type, id, and version.
• Reviewer and review timestamp.
• Proposed action.

Human Rule

Humans decide quality. AI may summarize notes, normalize categories, and suggest likely blame stages, but only human-confirmed feedback becomes the durable QA record.