{"slug":"marking-assistant","name":"Rubric Feedback Drafting","category":"Education","customer":"Heads of English or History in secondary schools","problem":"Teachers spend evenings typing repetitive comments into student work, so feedback shrinks to a few hurried lines.","value":"For Heads of English or History in secondary schools, turn student submissions and a marking rubric into draft feedback comments with cited evidence and a next action. Address the recurring problem: teachers spend evenings typing repetitive comments, so detailed feedback shrinks to a few hurried lines. The value hypothesis is a faster, more consistent feedback process with teacher oversight; the pilot must establish whether teachers trust and adopt the drafts.","format":"Source-based content workspace with editorial delivery","screens":"Key screens: Upload queue, rubric setup, draft review. Use a batch upload screen for student files, a rubric mapping screen for criteria, and a review queue showing one student's draft comments per criterion with evidence highlights. Allow inline editing and a toggle to view the original submission. Provide an approve-all button with a confirmation step. In this product, the first view is upload queue, followed by rubric setup and draft review.","functionality":"1. Extract text from student submissions. 2. Map each submission against rubric criteria. 3. Draft a three-sentence comment per criterion with evidence. 4. Flag contradictions or missing evidence. 5. Present drafts in a review queue for editing. 6. Export approved feedback to a spreadsheet or LMS-ready format.","workflow":"Upload student files, set rubric criteria, run the drafting process, review drafts in the queue, edit comments, approve the batch, and export feedback. Start with student submissions and a marking rubric and finish with approved feedback comments ready for the LMS.","ai":"Use language models to read each submission, extract evidence, and draft comments against rubric criteria. Flag logical inconsistencies or missing evidence automatically. A teacher reviews every draft and approves or edits before anything is released; no comment reaches a student without human sign-off.","inputs":"Student submissions and a marking rubric","deliverables":"Approved feedback comments with cited evidence and next actions","admin":"Teacher accounts, batch versions, rubric versions, approval states, edit history, export logs, and a record of which comments were edited versus approved as drafted.","mvp":"A single-teacher pilot accepting Word documents and a plain-text rubric. First two modules: text extraction and draft generation. Manual review in a spreadsheet output.","expansion":"Automate formatting for specific LMS fields, add batch approval workflows, and introduce a feedback history per student to track progress over terms.","usp":"Drafts cite specific evidence from each student's own text, so the feedback is grounded and personal rather than generic.","defensibility":"The rubric mapping and evidence extraction improve with more use, creating a feedback style profile per teacher that becomes harder to replicate.","alternatives":"Teachers type comments manually or use generic comment banks. This differs by generating tailored, evidence-based drafts that still require teacher approval.","revenue":"Test pricing at USD 49 per teacher per term, with a departmental discount for five or more licences.","costs":"Language model API usage per submission, basic hosting, and minimal support overhead.","integrations":"Start with CSV export for LMS import, then add Google Classroom and Moodle APIs.","dependencies":"Reliable text extraction from common file formats and a stable language model API for drafting.","pilot":"A paid pilot with one secondary school department proves it by measuring time spent on feedback per batch and teacher approval rate. Baseline is current manual time; success is a 30% time saving with at least 80% of drafts accepted without major edits.","plan30":"Week 1: Build text extraction and rubric input. Week 2: Implement draft generation with evidence citation. Week 3: Create the review queue and export. Week 4: Run a single-teacher pilot and collect feedback.","metrics":"Time saved per marking batch and percentage of drafts approved without major edits.","channels":"Education conferences, teacher forums, and direct outreach to heads of department via school email lists.","leadMagnet":"A free sample report showing draft feedback for one uploaded student submission.","message":"Draft personalised feedback for every student against your rubric, so you edit and release instead of starting from a blank page.","retention":"The tool becomes part of the marking cycle each term; usage history and saved feedback styles make switching back to manual work costly.","controls":"Teachers must approve every comment before export. The system must not release feedback automatically, must not alter grades, and must flag any submission it cannot read clearly for manual review.","crossSector":"Human Resources; Legal","fn":["Extract text from student submissions","Map each submission against rubric criteria","Draft a three-sentence comment per criterion with evidence","Flag contradictions or missing evidence","Present drafts in a review queue for editing","Export approved feedback to a spreadsheet or LMS-ready format"],"sc":{"opp":6,"pain":7,"feas":9,"now":8},"phases":[{"name":"MVP","scope":"One buyer segment, one recurring use case; first modules: text extraction and draft generation. Manual review in the loop.","time":{"days":2,"label":"2 days"},"usd":5000},{"name":"Paid pilot","scope":"Accounts, roles, review states, audit trail and the first integration, hardened for two to three paying pilot customers.","time":{"days":3,"label":"3 days"},"usd":4000},{"name":"Full product","scope":"Self-serve onboarding, billing, monitoring and the wider integration set.","time":{"days":5,"label":"5 days"},"usd":6000}],"running":[{"stage":"MVP and paid pilot","note":"about 3 customers","hosting":[30,60],"ai":[70,140],"total":[100,200]},{"stage":"Full product","note":"about 50 customers","hosting":[110,210],"ai":[700,1400],"total":[810,1610]}],"total":15000,"complexity":0.01,"days":10,"shot":true,"demo":true}