Skip to content
Log in

Rubric Design

Anchors each level with observable evidence, without which every scorer applies a private standard.

0

Share this prompt

Free — no card needed

Create a free account

to open Rubric Design — and the other 364 prompts across 21 categories.

We store your email address to send these. We never sell it or pass it to advertisers. Withdraw at any time. Privacy Policy.

Already have an account?

CategoryEducationForEducators, OperatorsTested onClaudeChatGPT

Running it, start to finish

  1. Write level descriptors as observable features of the work.
  2. Define what separates each adjacent pair of levels.
  3. Calibrate scorers on sample work before marking anything real.

What you get back

The output this produces, every time.

  • Writes descriptive level anchors rather than evaluative labels, so two scorers can agree.
  • Names what distinguishes adjacent levels, which is where nearly all disagreement happens.
  • States what is deliberately not assessed, which otherwise leaks into scoring.

Getting better results

Where this usually goes wrong, and how to avoid it.

  • Use fewer levels. More levels sound precise and reduce agreement, because the distinctions stop being applicable consistently.
  • Run a calibration session. Two scorers marking the same three samples independently does more for consistency than any rubric rewrite.
  • Issue it with the task. A rubric given in advance changes what learners produce. One used only for marking does not.

More Education prompts

All Education

Written for The AI University. Every prompt in this library is original work — authored, tested and revised here, not collected from elsewhere. 365 of them, free with an account.