Combine model answers, rubrics, ordered provider fallback, pending-grade status, and manual review so automation assists the grader instead of replacing judgment.
Before you start
Own the quiz, configure at least one enabled AI provider, and keep its credential private. AI authoring and correctness-review controls require Premium or above; answer grading also needs a model answer on each enabled question.
Work through the product
Create a Free Text question, add a concrete model answer and optional rubric, then enable AI grading. In AI settings, save and test providers in priority order. After submission, use Analyze and Grade to inspect suggestions, adjust points or comments, and finalize any answer left pending or sent to manual review.
Expected result
Automatically graded answers move through pending to a suggested score; failures fall through the configured provider order and then remain available for human grading.
Limits, privacy, and control
Never place API keys in question text, screenshots, or shared documentation. Review AI suggestions before relying on them; a human grade takes precedence and unsupported or failed requests fall back safely.