See how a grade was reached.
Review a criterion-by-criterion breakdown. Maths is checked mathematically first, and worked references help make partial credit consistent.
Your rubric choices, grading rationale, and corrections shape an AI partner that aligns with your approach. Two independent opinions and blind calibration keep that alignment open to review.
Find and classify the stationary point.
Two independent AI graders assess each answer. Mathematical equivalence is checked first, and rubric criteria make partial credit and disagreements visible.
A worked reference supports partial credit. Both graders explain the marks through the rubric.
Disagreements are shown to you. Grades are never silently reconciled.
Illustrative product walkthrough · sample dataReview a criterion-by-criterion breakdown. Maths is checked mathematically first, and worked references help make partial credit consistent.
In Second Look, grade sample assessments before seeing AI marks. Compare rationale and scores, inspect disagreements, and focus first on students whose letter grade or pass/fail could change.
Edit a rubric to re-grade the question across the class. Manual grades stay protected, and results are held until you approve them.
Exports stay marked DRAFT until approval. Approving without a full review requires a written, logged reason.
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.
Equivalent answers are proven correct instantly. A pre-solved reference makes partial credit consistent. Showing work is expected by default, and calculus tiers apply.
Graded by the rubric, criterion by criterion, with the breakdown visible to the instructor.
Sketches graded from the drawing: shape, intercepts, asymptotes, end behaviour.
Identical answers always get identical grades.
Grades in seconds after a student submits.
Turn the results into what comes next.
Grades are held until an instructor approves them. Second Look brings grading disagreements, calibration, low-scoring questions, and integrity review into the same process. Exports remain marked DRAFT until approval.
The disagreement is shown to the instructor with both grades and a criterion-level comparison. The instructor can select either opinion or enter a grade. Manual grades are protected from automatic regrading.
Bring your assessment workflow. See how privacy-conscious proctoring and AI co-grading can support your teaching.