Pawtograder vs Rubrical

Pawtograder combines autograding, manual grading, office hours, discussion, a gradebook, and analytics for computer science courses. Each commit can trigger tests through GitHub Actions, with results shown by test in the grading interface. Rubrics support additive, deductive, and multi-level criteria, line-level annotations, and separate scoring for group members. The gradebook includes MathJS expression columns, drop-lowest calculations, CSV import, and a student what-if mode. Office hours queues support text, video, and screen sharing, and can show linked submissions and failing tests. Discussions can surface relevant threads for known errors and allow public or staff-only posts. Calendar feeds and Discord channel mirroring cover course events; LTI 1.3 integrations with Canvas, Blackboard, Brightspace, and Moodle are listed as roadmap items. Optional AI-generated test hints and an MCP server for compatible AI clients are also listed. Instructors can use the project-hosted community instance or self-host on Kubernetes with Helm charts. The project is GPLv3 open source. The free community instance is for evaluation; ongoing use at scale requires contacting the project.

Rubrical is a web-based AI teaching platform for geography departments. Teachers can upload PDF, Word, or image assessments and mark schemes, or create rubrics themselves. It marks answers criterion by criterion against the selected rubric, presents reasoning and evidence, and drafts feedback; a teacher approves every mark and feedback item before delivery to students or writing to an LMS. Rubrical also drafts specification-aligned objectives, timed lessons, and tiered resources grounded in checkable sources. Approved results produce assessment-objective breakdowns, question-difficulty rankings, at-risk flags, misconception heatmaps, and plain-English queries. Work can come from Google Classroom, Microsoft Teams, scans, or student hand-in links. It supports AQA, Edexcel, OCR, WJEC/Eduqas, and user rubrics. Feedback can be simplified, enlarged, shown in OpenDyslexic, or translated. Core school data is stored in London. Rubrical says student and learning-platform data are not used to improve AI models. Pricing is available by contacting the team.