Grade free-response work¶
Open Grade¶
Open an exam and select Grade. The workspace is pinned to the displayed Administration version. The overview contains a question selector, an Auto-graded entry when applicable, grader assignments, exam-wide queues, recommended action, bulk review, available queues, and optional embedded course AI settings.
Select a free-response question to open its Question & Rubric and Assessment tabs. Graders reach assigned questions from Grading assignments and see only permitted controls.
Publish a rubric revision¶
In Question & Rubric, edit the rubric draft. Describe how to award points, deductions, caps, and treatment of common errors; do not merely provide a worked solution. Save/publish creates an immutable numbered rubric revision. Select the canonical revision when more than one exists.
Rubric AI, when enabled, runs only after an explicit action:
- Suggest proposes a rubric from the problem and any optional instructions. Preview the proposal before applying it to the editable draft.
- Vet reviews the exact displayed draft or selected published revision, reports selective findings, and proposes a minimally changed complete rubric only when findings exist. Applying replaces only the draft.
Neither action publishes a rubric. If its inputs change, a completed result is marked out of date.
Changing the canonical rubric makes previously approved finals from another revision Re-review and gives provisional assessments a rubric-version warning. Use batch re-review only when the change is trivial and the existing scores and assessments genuinely still apply.
Understand question status¶
| Status | Meaning and next action |
|---|---|
| Needs rubric | Publish/select a rubric before grading can proceed. |
| No AI | Accepted work is ready; grade manually or generate AI candidates. |
| Needs review | At least one usable AI candidate exists; a person must review and save the final. |
| Provisional | Eligible AI agents agreed and policy allowed provisional approval; a person must approve it. |
| Re-review | A saved final used a different rubric revision. Review again or use the explicit trivial-change batch action. |
| Approved | An instructor or assigned grader approved the final against the current rubric. |
Only accepted work from current packets enters the ordinary queues. Resolve scan and packet conflicts first when possible.
Generate AI candidates¶
The default controls use the saved course policy and active agent order:
- Generate subset launches fresh runs for the inclusive from/to positions; the range is saved per user and question.
- Generate remaining targets responses with no completed candidate assessment for the current rubric.
- Generate all launches fresh runs for every accepted response and confirms when existing candidates are present.
Each generation uses the course policy and rubric in effect when it starts. Later configuration changes affect future work only.
AI candidates are proposals, including when agents agree. A one-model run cannot provisionally approve. See Configure AI features to change the course policy.
Review and finalize one response¶
Choose a status queue or an individual segment in the status bar. The review page shows response evidence, Candidates, Rubric, and Question reference tabs, and the final Assessment editor.
- Inspect every accepted response crop for the target question.
- Read the canonical rubric and published question context.
- Open candidate details as useful. Copy to assessment copies a proposal's score and student-facing assessment text into editable final fields; it does not approve automatically.
- Enter a score from zero through the question maximum and edit the assessment LaTeX.
- Save the final. The queue advances according to the selected review mode.
Use the missing-work path when the current packet should receive a score without an accepted response. If work is scanned later, Gradebird asks you to resolve the conflict before replacing that grading decision.
Candidate thumbs-up/down feedback records quality feedback for Gradebird review; it does not change the grade.
Bulk review provisional assessments¶
Select Bulk review from the overview or a question. Review the visible rubric, response images, score, and assessment for every selected item. Approve only the checked assessments. An option can revoke other selectable provisional assessments left unselected; otherwise they remain provisional.
If a provisional assessment references a stale rubric, either confirm that the change is trivial after review or revoke provisional status so it returns to the current-rubric queue. Bulk review never removes the requirement for human judgment.
AI solution and candidate comparison¶
The AI Solution panel asks the current primary grading models to solve the published problem independently. Changes to the problem, course context, or primary-agent selection make the prior solution review out of date. Disagreement or serious issues are advisory and do not validate or invalidate the rubric automatically.
Candidate summaries compare assessments when at least two current-rubric candidates exist. Instructors may archive a candidate from the current view and restore it later.
Completion boundary¶
Provisional candidates and stale finals do not make grading release-ready. Every gradeable free-response question on the canonical packet must have a current approved final. Auto-graded questions separately require a current definitive recognition and score against the current key. Then continue to Reports and exports.
Grading assignments¶
This page lists the published questions assigned to a grader across courses and exams. Each row summarizes remaining review work and links to the permitted question workspace or grader overview. The page does not grant broader course access than the saved assignments.
Grading overview¶
This grader-facing overview summarizes only the questions assigned to the current grader for one exam version. It provides question navigation, progress, and recommended next actions while respecting rubric-edit and student-name permissions.
Manage grades¶
The instructor overview coordinates question selection, rubric readiness, grader assignments, auto-graded work, review queues, and exam-wide progress for the administration version. Use it to choose the next grading action; counts and recommendations do not themselves approve or change grades.
Grade a question¶
This workspace manages one published question’s rubric and assessment workflow. Depending on permission, an instructor or grader can inspect the question, publish or select a rubric revision, launch eligible AI assistance, review queue state, and move into individual or bulk review. A selected tab is local page state and does not change the question identity.
Review a free-response submission¶
This page reviews the accepted scan evidence, current rubric, AI candidates, provisional state, and final assessment for one response. Authorized users can generate eligible candidates, select or edit an assessment, approve a final, revoke a provisional result, or navigate the active queue. Saving a final is the consequential grading boundary.
Bulk review provisional assessments for an exam¶
This page groups provisionally approved assessments across the displayed exam version. Review the evidence and current-rubric status before approving selected results; stale or ineligible items require individual handling. Opening the page or selecting rows does not finalize them.
Bulk review provisional assessments for a question¶
This page applies the same bulk-review rules to one published question. It narrows the visible set but does not weaken rubric, permission, or human-review requirements.
AI solution details¶
This detail page shows the outcome and provenance of an instructor-requested AI solution check for a published question. It can explain agreement, warnings, and the models involved, but the check remains advisory and cannot publish content or approve grading.
AI assessment details¶
This page shows one candidate assessment, its score, assessment text, notes, and available provenance. Instructors use it to compare candidate reasoning with the rubric and response evidence; viewing a candidate does not make it final.
AI grading run¶
This page summarizes one saved-policy grading run, including attempts, selected candidate, and the policy snapshot used when it started. It is historical evidence: later course or agent changes do not rewrite the run.
Deliberative grading run¶
This page presents the rounds and recommendation from a historical deliberative grading run. It supports review of existing records but does not expose the developer/tester launch controls as a supported instructor workflow.