Overview
Tuition.in has two separate AI grading flows:
- Test answer grading — triggered automatically when a student submits a test containing subjective questions (short text, long text, or file upload). No creator action needed.
- Assignment submission grading — creator-initiated. You open a submission, optionally run OCR on uploaded files, then click Run AI orRun + Apply to get a score and feedback you can accept or override.
Both flows use the same rubric-based evaluation by a language model.
What the AI grades
| Question / submission type | AI involvement | Trigger |
|---|---|---|
| MCQ, multi-select, true/false, fill-blank | None — deterministic auto-grade | Automatic on submit |
| Short text (test) | Scores against rubric, provides feedback | Automatic on submit (background) |
| Long text (test) | Scores against rubric, provides paragraph feedback | Automatic on submit (background) |
| File upload (test) | OCR → grade extracted text against rubric | Automatic on submit (background) |
| Assignment submission | Scores text + OCR against rubric + blueprint | Creator-initiated (manual button click) |
OCR pipeline
OCR (Optical Character Recognition) is used when a student submits an image of handwritten work. The pipeline works as follows:
- The student's uploaded file URL is inspected. Only image URLs (JPEG, PNG, WebP) are eligible — PDF files are skipped (see limitations below).
- Each image URL is passed to the OpenAI vision API (
gpt-4o-miniwith the image in the message). The model extracts all readable text from the image. - Extracted text from all images is concatenated into a single block called
ocrText. - The AI grader then evaluates
ocrTextagainst the rubric, exactly as it would evaluate a typed text answer.
For assignments, OCR can be run on a student's uploaded files even before AI evaluation. Click Run OCR in the submission panel to extract text, review it, and then run AI evaluation.
Writing a good rubric
The quality of AI grading is directly proportional to rubric quality. A vague rubric produces unreliable scores; a precise rubric produces scores a human teacher would recognise as fair. A test question's rubric is set in the question editor; an assignment's goes under Marking guide → Rubric.
Structure your rubric as a list of scorable criteria:
- State the maximum marks for each criterion explicitly.
- Describe what earns full marks, partial marks, and zero for each criterion.
- For factual questions, list key terms, formulas, or dates that must appear.
- For conceptual questions, describe the reasoning chain that must be present.
Example — 10-mark question on photosynthesis:
Assignment AI evaluation
Assignments (created within a batch) support AI-assisted grading in addition to manual grading. The workflow:
- Give the assignment a rubric, an answer key, or both, under Marking guide when you create it or press Edit on it. See below.
- A student submits their answer (text, file URLs, or both).
- In the batch's assignments, press Submissions on the assignment.
- Optionally run OCR if the student uploaded images.
- Click Run AI to see the AI's score + feedback before applying.
- Click Run + Apply to run AI and immediately apply the score.
- Review, override if needed, and click Save grade.
Answer key
An answer key is what a full-marks answer contains: a model answer, a worked solution or a correction guide. The AI compares each submission against it. It helps most with:
- Maths or physics problem sets where the step-by-step solution matters.
- Language assignments with a sample essay or expected content structure.
- Standardised tests where a marking scheme is published.
To add one, open the assignment's Marking guide (when you create it, or press Edit on it) and type or paste the key into Answer key, up to 20,000 characters. It is kept with the assignment and used for every submission you evaluate.
Running AI evaluation
In the grading panel for a submission:
- Run AI — evaluates the submission and displays the AI's suggested score and feedback. Does not update the stored grade. Use this when you want to inspect the AI output before committing.
- Run + Apply — evaluates and immediately saves the score + feedback as the student's grade. The student is notified. You can still override afterward.
Both options show a per-criterion rubric breakdown (if a rubric was set) in an expandable table: each row lists the criterion, the awarded marks, the maximum, and a short AI comment.
Reviewing & overriding AI grades
After AI evaluation (whether from a test or assignment), the final grade panel at the bottom of the grading view allows you to:
- Edit the Score field — type any number from 0 to max. The AI-suggested value is pre-filled.
- Edit the Feedback field — pre-filled with AI feedback. Personalise it or replace it entirely.
- Click Save grade to commit.
When you manually override an AI grade, the submission is marked with gradedBy: MANUAL. When the AI grade is applied as-is, it's marked gradedBy: AI. This is shown as a badge on the submission.
Confidence scores
The AI returns a confidence score (0.0–1.0, shown as a percentage) with every subjective grade. This reflects how certain the model is about its assessment.
| Confidence | Interpretation | Recommended action |
|---|---|---|
| 80–100% | High. Clear match or mismatch with rubric. | Safe to apply directly in most cases. |
| 50–79% | Moderate. Answer is partially correct or ambiguous. | Review the rubric breakdown before applying. |
| < 50% | Low. Unclear answer, unusual response, or rubric ambiguity. | Grade manually — don't rely on AI score. |
Low confidence can indicate: the student wrote in a language other than the rubric, the answer is a diagram description that doesn't map to text rubric criteria, or the rubric is underspecified.
Student notifications
Students are notified when:
- A test is submitted — they receive an immediate notification with their objective score and a note that subjective questions are being graded.
- AI grading completes for subjective test answers — the score is updated and a follow-up notification is sent.
- An assignment is manually graded or AI grade is applied — the student receives a notification with their score and feedback summary.
Students can see the full rubric breakdown, per-criterion feedback, and AI confidence score in their test results view.
Limitations & edge cases
- PDF OCR not supported. Only JPEG, PNG, and WebP images are processed. Ask students to photograph or screenshot their work.
- Non-English answers. The model handles Hindi, Tamil, and other major Indian languages reasonably well, but accuracy is lower than English. If your course is in a regional language, always review AI grades before applying.
- Mathematical notation. Typed LaTeX or equations are understood by the model. Handwritten maths in images depends on OCR quality — messy handwriting may confuse the extraction step.
- Rate limits. AI grading calls are subject to OpenAI rate limits. During a large batch submission (e.g., 100 students all submitting within 60 seconds), a few grading jobs may be delayed by 30–60 seconds. Students see a "grading in progress" state until their job completes.
- Hallucinated scores. In rare cases the model may award scores that don't match the rubric. The confidence score is your early warning — treat anything below 50% as a signal to check manually.