Prepare an analytic scoring checklist for a science poster

An analytic scoring checklist with separable criteria and observable level descriptors.

Choose one of three approaches. The steps for that option appear below.

Choose an option above. On a phone, swipe the tabs left or right to see all options →

ChatGPT: maps criteria, then drafts performance levels

ChatGPT maps evidence to separable criteria, then drafts level descriptors in the same chat. You check each stage.

  1. You

    Get ready

  2. ChatGPT

    Map the criteria

  3. You

    Correct the map

  4. ChatGPT

    Draft the levels

  5. You

    Apply and check

  1. Have ready: brief, outcomes, samples

    Use: You

    The science-poster brief, the outcomes and sample success evidence. Upload them to one ChatGPT chat.

    Check

    Use only the supplied brief, outcomes and samples as authority. Check your class data policy allows the upload.

  2. Map evidence to criteria, flag double-counting

    Use: ChatGPT

    Ask ChatGPT to map intended evidence to separable criteria and flag double-counting risks.

    Details

    What to paste into the tool

    Task: Draft criterion-to-outcome map with double-counting risks. Map the intended evidence in this brief to separable criteria: one row per candidate criterion with the outcome it serves, observable evidence examples from the samples, and any double-counting risk between criteria. Flag criteria that measure taste rather than the outcomes.

  3. Check intent and correct the criterion map

    Use: You

    Check assessment intent, remove irrelevant aesthetic preferences and correct the criterion map. Keep unresolved items.

    Check

    Check each criterion is separable.

  4. Draft performance levels with descriptors

    Use: ChatGPT

    Paste the corrected map. Ask for performance levels with observable descriptors for each criterion.

    Details

    What to paste into the tool

    Task: Draft analytic scoring checklist with performance levels and observable descriptors, not yet applied to samples. Using only this corrected criterion map, draft performance levels for each criterion with observable descriptors that differ in evidence, not in vague degree words. Keep unresolved items visible and keep criteria separable.

  5. Apply it to sample posters and check

    Use: You

    Apply the draft scoring checklist to sample posters and check adjacent levels can be told apart.

    Check

    Check adjacent levels can be distinguished and every item matches the approved sources. Preparation only; do not submit learner work, publish material, alter official grades or make placement decisions automatically. No inline citations back to the brief or samples are confirmed, so the teacher verifies the map against the sources directly. Criterion mapping and scoring checklist drafting rest on the teacher's own checks; no official wording confirms these operations.

Before you paste into any AI tool, remove any confidential information. Put it back at the end.

Tools in this workflow

Deciding between ChatGPT and Claude for this? See the comparison.

Final check

Teacher confirms assessment intent and removes irrelevant aesthetic preferences before levels are drafted.

Teacher applies the draft scoring checklist to sample posters and verifies adjacent levels can be distinguished.

Criteria must map to outcomes; levels must differ in observable evidence and no aspect may be double-counted. Preparation only. You review the result; do not submit learner work, publish material, alter official grades or make placement decisions automatically.

Check the result against your original inputs. Approve it before sharing or acting.

What still needs checking
  • No cited evidence confirms criterion mapping, outcome alignment or descriptor boundary checking as operations; every option rests those on the teacher's gates.
  • Whether the class Khan Academy account meets the teacher-role and supported-language requirements is unchecked.

Share this page