# AI grading

> AI grading works best when you treat the model like a trained teaching assistant: give it a clear job, explicit standards, and examples of what good and weak work look like. Put shared…

Source: https://www.curacourse.com/help/best-practices-for-ai-grading

## At a glance

AI grading works best when you treat the model like a trained teaching assistant: give it a clear job, explicit standards, and examples of what good and weak work look like. Put shared policy in **Grading Context**, and put measurable dimensions in **Scoring Criterion**. These practices match the **Info** help inside the AI Grading item in the lesson editor.

## Prerequisites

- An activity with an **AI Grading** rubric item. See **Add rubric items (manual, AI, and code grading)**.

## 1. Separate instructions from criteria

Use **Grading Context** for global rules: course norms, tone, partial-credit philosophy, and what counts as full credit.

Use **Scoring Criterion** (and the **Criterion Name**) for one measurable dimension — accuracy, reasoning, completeness, use of a required method, and so on.

Mixing both in one block makes scores harder to reproduce. Put shared context on the **first** AI item in the group; later items can add extra context if needed.

## 2. Write criteria as observable behaviors

Describe what appears in the student’s answer, not what you hope they understood.

- Prefer: *names the correct algorithm and explains time complexity*
- Avoid: *shows good understanding*

Observable language reduces drift between runs.

## 3. Define every point level

**Weight** sets both the item’s points and how many levels you must describe (0 through that number). Fill every level. The model anchors on these bands; vague middle descriptions produce inconsistent partial credit.

When in doubt, add a short example phrase at each level (what a 0, 1, and 2 actually look like).

Keep **Weight** modest at first (2–3 points). Changing weight resizes the descriptor slots, so write levels after you settle on the scale.

## 4. Keep criteria independent

Add a separate AI item per dimension instead of packing unrelated ideas into one descriptor. Avoid double-counting: if “correctness” and “uses proper terminology” overlap heavily, merge them or narrow each so one mistake is not penalized twice.

## 5. Calibrate with test grading

Before you assign the lesson, submit sample responses that represent a clear pass, a borderline case, and a fail. Adjust descriptors until scores match your intent. Re-test after you change **Grading Context**, keywords, or point totals.

## 6. Tell the model how to handle ambiguity

In **Grading Context**, state whether to:

- Reward reasonable paraphrasing
- Deduct for missing optional details
- Enforce strict spelling, units, or notation

Explicit policies prevent harsh or overly lenient outliers.

## 7. Request actionable feedback

Ask for brief student-facing feedback tied to the criteria (what was strong, what to fix). That helps learners, and it helps you see when the rubric itself needs work.

Instructors also receive private **Instructor Info** notes in grading results. Use those to audit the model; do not rely on Lightning Grader to edit the AI score row — adjust with [score modifiers](https://www.curacourse.com/help/score-modifiers-bonuses-and-deductions) or general feedback if needed.

## Keywords

**Keywords** are optional hints, not a checklist the student must hit verbatim. Use them for course-specific terms you want emphasized. Do not expect all-or-nothing keyword matching.

## Start simple

Two or three criteria with clear levels is enough. Add complexity only when test grading shows a consistent gap.

On a Code Editor, AI grading reads the submitted files as text. Use it for design, style, or explanation — not as a substitute for **Code Grading** tests that check actual output. See **Best practices for code grading**.

## Related articles

- [Rubrics & scoring modes](https://www.curacourse.com/help/rubrics)
- [Grade a lesson with Lightning Grader](https://www.curacourse.com/help/grade-a-lesson-with-lightning-grader)
- [Score Modifiers: bonuses and deductions](https://www.curacourse.com/help/score-modifiers-bonuses-and-deductions)
- [Add rubric items (manual, AI, and code grading)](https://www.curacourse.com/help/add-rubric-items-manual-ai-and-code-grading)
- [Best practices for code grading](https://www.curacourse.com/help/best-practices-for-code-grading)