Help Center
Grading and feedback

Giving the grader materials and references

Hand the assistant what students worked from (a case, the reading) and the standards you grade against (a citation manual, a house format).

Updated September 21, 2026

Your rubric captures the criteria and their weights, but not the documents that sit behind them. There are two kinds, and the assignment page has a place for each:

  • Materials, on the Assignment row: what students were given to work from. The case file, the statute, the fact pattern, the set reading.
  • References, on the Rubric row: the standards you grade against. A citation manual, a house memo format, a style guide.

Where you put a document is how the assistant knows what it is. There is nothing else to choose.

Materials: what students worked from

Choose Materials on the Assignment row and the drawer opens under it. Materials belong to this assignment only: reuse the rubric for next month's memo and last month's case file stays behind.

The assistant treats materials as the source of truth on their own contents. When a paper states a fact, a holding, a date or a figure that conflicts with the case file, it says so specifically. It also recognises passages students quote from the materials, so quoted text is never credited, or marked down, as the student's own writing. Choosing the right authority and applying it still counts: that is the student's work. Feedback may point a student back to a document by name.

If the assignment limits students to the materials you provided, say so in the assignment prompt. The assistant reads the prompt and the materials together.

References: how papers are judged

Choose References on the Rubric row. References travel with the rubric to every assignment that uses it, which is what you want for a citation manual you enforce all year.

Each reference has an Applies to setting: Whole paper, one criterion, or several. Point the Bluebook at your Citation criterion and the assistant uses it there and nowhere else. When you upload a reference, the assistant suggests which criterion it belongs to; the suggestion is marked with a dashed border until you confirm or change it.

A reference only matters if a criterion measures it. A style guide on a rubric with no formatting criterion has nothing to score. To say more about how a reference should be used, write it in that criterion's AI note in the rubric builder.

Adding a document

Both drawers work the same way. Drop a file, or add one from Google Drive or OneDrive. PDF, Word .docx, and plain text are all read. You can paste text instead if what you want to hand over is not a file.

Each document keeps its original: choose the eye to read it again, or the download arrow to save a copy. Removing a document deletes the file too. Everything autosaves.

The context budget

Materials and references share one budget per paper, because both are read on every paper graded. Each drawer shows the combined total, with its own share in the darker colour. If it goes over, the meter turns red: trim a document before the assignment grades.

Long documents are condensed once, when you upload them, so they fit. The row says condensed to when that happened, and the eye shows exactly what the assistant reads. For a document where every word matters, upload just the pages that do.

Wrong answers and feedback cues

These used to live here as rubric-wide lists. They belong to a criterion, so they are written in a criterion's own AI note in the rubric builder now. Anything you added before still works exactly as it did, and you can still edit or remove it under References.

What it does not do

  • Students never see it. Materials and references shape grading; they do not appear on reports or anywhere student-facing.
  • Web links are not followed. A pasted URL is just text to the assistant. Upload the document itself, and refresh it yourself when the source changes.
  • They add no criteria. The assistant grades what your rubric names, using these documents to decide what is true and what the standard is.
  • Whole graded papers do not belong here. A model answer or a scored exemplar is a validation paper: see Validating the grader against your grading.

Was this helpful?

Keep reading

  • Uploading papers — Which files work, how a stack is matched to students, and what each status in the paper list means.
  • How grading works — The assistant proposes; you decide. How scores are made and how you stay in control.
  • Scoring a criterion with rules — When a criterion is a checklist rather than a judgment: Binary and Count rules, adding up or deducting, and what the rail shows.
  • Validating the grader against your grading — Run a few papers you have already graded on the Validate step, so the assistant learns how you actually score before it grades the class.
  • Grading a whole class at once — Once validation satisfies you, grade the whole set in one pass, then review the results.
  • Reviewing and adjusting the feedback — Adopt the assistant's observations you agree with, dismiss the rest, and write your own.
  • Reading the grade rail — How much of the AI's read to show, where each score came from, what the look-fors say, and how to filter the margin.
  • Marking up a paper — The grading page: the pen tools, your own comments, suggested rewrites, what students see, and undo.
  • The assistant, and talking to it — The three places you can ask the assistant for help, what each one knows, and how to dictate instead of type.
  • When a grade needs a second try — Stopping a run, re-grading a paper, what a failed or incomplete grade means, and what happens during an AI outage.
  • Your comment library — Every comment you write collects in one library: browse it while grading, insert with a keystroke, and bring in the comments you wrote before.
  • Comment suggestions in your own voice — As you write a margin comment, LawGrader suggests the rest of it, drawn from the comments you have written before.