AI Assessment
How the Assessment Agent grades open-ended responses and provides learner feedback.
The Assessment Agent automatically grades responses that can't be scored by simple keyword matching — short answers, essays, and AI Dialogue conversations.
What the Assessment Agent grades
| Block / Question type | What's evaluated |
|---|---|
| Short Answer questions | Response against a rubric or model answer |
| Essay questions | Response against a rubric or model answer |
| AI Dialogue blocks | Full conversation against learning outcomes |
Short Answer grading
Short Answer questions support two grading modes. The Assessment Agent:
- Reads the learner's response
- Compares it semantically to your rubric or model answer (not just keyword matching)
- Assigns a score based on how well the key points are covered
- Optionally provides written feedback
Setting it up:
- In the Quiz block, add a Short Answer question
- In the AI Grading Configuration section, set the grading mode:
- Rubric — describe the key points the answer should cover
- Model Answer — provide an ideal answer to compare against
- Fill in either the criteria or the model answer depending on the mode you chose
- Optionally add feedback text for learners
Essay grading
Essays, like Short Answers, support two grading modes.
Setting it up:
- Add an Essay question to a Quiz block
- In the AI Grading Configuration section, select the grading mode:
- Rubric — provide grading criteria describing what to look for
- Model Answer — provide an ideal answer
- Complete the corresponding field (criteria or model answer)
- Set the maximum score
The Assessment Agent reads the learner's essay, evaluates it against your criteria or model answer, assigns a score, and writes personalized feedback explaining what was done well and what could be improved.
Tip: The more specific your criteria, the more consistent and useful the grading. Vague criteria produce vague feedback. If you want multiple criteria, list them in the grading criteria text (e.g., "Should address: Clarity, Accuracy, Examples").
AI Dialogue grading
After a learner finishes an AI Dialogue conversation, the Assessment Agent reviews the full transcript.
What it evaluates:
- The full conversation transcript against the block's Learning Outcomes — what learners should demonstrate in the conversation
A score and written debrief are shown to the learner at the end of the dialogue.
Setting learning outcomes: In the AI Dialogue block settings, define the Learning Outcomes — a list of what learners should demonstrate in the conversation. The AI grades the full dialogue transcript against these outcomes. There are no separate goal, success criteria, or scoring dimensions fields.
Scores and records
All AI-assessed scores are:
- Recorded in the learner's progress record
- Visible in the Learners dashboard
- Included in overall course completion calculations
Instructors can review individual scores and feedback from the learner detail view.
Limitations
- AI grading is high-quality but not infallible. For high-stakes assessments, consider manual review.
- Grading consumes AI credits.
- Feedback is generated in the course's configured content language.