AI grading with educator oversight

Two independent AI graders

Two models grade each answer independently. One provides the official proposed grade and the other a second opinion. Disagreements are shown to the instructor and never resolved silently.

• Instructor-aligned co-grading is shaped by co-authored rubrics, grading rationale, and corrections, with alignment checked through instructor-led review.

Maths checked mathematically first

Equivalent answers are proven correct instantly. A pre-solved reference makes partial credit consistent. Showing work is expected by default, and calculus tiers apply.

Criterion-by-criterion grading

Graded by the rubric, criterion by criterion, with the breakdown visible to the instructor.

Grade sketches from the drawing

Sketches graded from the drawing: shape, intercepts, asymptotes, end behaviour.

Consistent grades for identical answers

Identical answers always get identical grades.

Grades in seconds after submission

Grades in seconds after a student submits.

Fix once, apply across the question

Edit a rubric and the whole question is re-graded. Change the points and existing grades rescale. Grades you set by hand are never overwritten.

Grades held for your approval

Grades held until you approve them.

An “at stake” review summary

How many students could still change letter grade or pass/fail, and about how many minutes of review are left.

Compare AI grading disagreements

Both AI grades side by side with a per-criterion comparison. Choose the AI’s grade, the second opinion, or your own.

Blind grading calibration

Grade a few random, high and low assessments without seeing the AI’s marks, then see how the AI compares and whether it leans harsher or more lenient than you.

• Blind calibration is part of Second Look. The instructor marks a sample without seeing the AI score, then compares the results and rationale.
• The aim is a personally calibrated co-grader that improves alignment over time and across courses.

Review low-scoring questions

Questions where the class average is under 50%: read every answer, fix the rubric, re-grade.

Integrity review in the grading flow

Integrity verification in the same flow.

Accountable approvals and DRAFT exports

Approving without a full review requires a written reason, which is logged. Exports are marked DRAFT until approval.

A practical, interactive gradebook

• One row per student with a square per question.
• Filters (needs grading, below 60%, integrity, ran out of time), search, and a heatmap matrix.
• Half-screen panels for a student or a question, with inline grading and keyboard navigation.

Branded PDFs with maths typesetting

• Student report: where marks were lost and what to work on.
• Answer sheet: the full record.
• Certificate and class roster.