Compare a learner's progress across repeated skill checks

A progress review with comparable skill evidence and stated limits from changed checks.

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 →

Gemini: builds the table, then drafts cautious trends

Gemini builds a skill-by-date table, then drafts cautious trends. You correct the table between passes.

  1. You

    Get ready

  2. Gemini

    Build the table

  3. You

    Correct the table

  4. Gemini

    Draft the trends

  5. You

    Compare and decide

  1. Have ready: the four dated checks

    Use: You

    Four dated fraction checks, skill tags, item counts and answer criteria.

  2. Build a skill-by-date table

    Use: Gemini

    Attach the checks to Gemini Apps web chat. Normalise attempts by skill and conditions into a skill-by-date table.

    Details

    What to paste into the tool

    Task: Skill-by-date table with denominators and changes. Using only the uploaded checks, skill tags, item counts and answer criteria, build a skill-by-date table with attempt IDs, denominators, conditions and missingness. Treat missing attempts as missing, not as failures, and flag any change in difficulty or conditions between checks. Mark uncertainty instead of inventing marks.

  3. Check marks and comparability, correct the table

    Use: You

    Check original marks and task comparability against the table. Correct it and keep unresolved items.

    Check

    Check every row against the original marks.

  4. Draft cautious trends and next checks

    Use: Gemini

    Give it the corrected table and ask for cautious trends and next learning checks.

    Details

    What to paste into the tool

    Task: Draft progress narrative with denominators and comparison limits. From the corrected skill-by-date table, draft a cautious progress review: describe observed performance only, keep denominators explicit, flag changed difficulty, and propose next learning checks. Do not infer mastery; mark uncertainty instead.

  5. Compare trends, then decide next checks

    Use: You

    Compare the trends with the corrected table and originals, then decide next checks.

    Check

    Check the narrative describes observed performance only, flags changed difficulty, claims no mastery, uses matched skills and explicit denominators, and keeps missing attempts missing. The chosen next checks change no grades or placement.

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

Compare the proposed trends with matched skills and explicit denominators, flag changed difficulty, treat missing attempts as missing, separate observed performance from inferred mastery and choose next checks without changing grades or placement.

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

What still needs checking
  • Actual fraction-check copies with original marks and criteria are not included in this authoring material; supply them at run time.
  • The quoted passage does not state this fraction-progress operation.
  • Fraction comparability, denominators and follow-up checks remain subject to teacher verification.

Share this page