Synthetic FRQ input
The source repo now includes fake learner responses and a teacher-defined rubric for a Precalculus linear model task.
Project Brief
Instructional AI Workflows
LMS-agnostic workflow prototypes for rubric-defined evaluation, draft feedback generation, human review, and student-facing artifacts.
Overview
Teacher-controlled AI assistance
The project frames AI as workflow support, not automatic grading: teacher-defined rubric -> structured evaluation -> draft feedback -> human review -> student-facing feedback, review, or remediation artifact.
Current Artifacts
- Precalculus FRQ synthetic rubric demo
- Three synthetic learner evaluations
- Two review-required feedback examples
- Structured evaluation JSON
- Teacher reviewer packet
- Reviewed student-facing feedback
- Remediation planning output
- Public safety rules for synthetic submissions and rubrics
Demo Evidence
What the current demo shows
Structured evaluation
The demo produces rubric-level evidence, scores, private teacher notes, and review-required flags for three synthetic learner examples.
Reviewed output
Only approved release notes are shown as student-facing feedback; teacher-facing review details remain separate.
Remediation planning
The demo groups rubric evidence into teacher-facing next steps for model setup, solving process, and context interpretation.
Safety Boundary
No private instructional records
Public demos must use synthetic submissions, synthetic rubrics, fake course identifiers, and public-safe sample outputs. Do not publish real student submissions, feedback, grades, comments, Canvas IDs, assignment IDs, course IDs, API tokens, or teacher-only review artifacts.