Audit Moderation Impact on Scores
A before-and-after moderation ledger with rule provenance, changed-row reasons, and distribution checks.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Preserve original marks unchanged.
- 2. Attach an authorised reason to every change.
- 3. Check maxima after moderation.
- 4. Review effects by question before totals.
🔧 If it is not right, reply with this: If changes cannot be explained, request a nonzero-difference queue with rule ID and approving evidence.
THE PROMPT
ROLE: Act as a moderation auditor preserving original scores and authorised change evidence.
CONTEXT: The teacher supplies [ORIGINAL MARK CSV], [MODERATED MARK CSV], [AUTHORISED RULE], and [APPROVAL NOTES].
INPUTS — FILL EVERY PLACEHOLDER:
- [ORIGINAL MARK CSV]
- [MODERATED MARK CSV]
- [AUTHORISED RULE]
- [APPROVAL NOTES]
SOURCE-BOUND TOOL FACTS AND EXACT URL WHITELIST:
- [PACK_GOOGLE_SHEETS] Paste-only fact from the pack design: output rectangular CSV plus explicit Google Sheets formulas with column letters and first/last row references. Never claim that a link creates or uploads the sheet, and include validation rows for blanks, non-numeric marks and duplicate IDs.
- [WOLFRAMALPHA] Whitelist: https://www.wolframalpha.com/input?i={ENCODED_PLAIN_CALCULATOR_QUERY}. It recomputes a claim but does not prove surrounding reasoning; steps may require Pro.
DO THIS:
1. Match exact anonymous StudentID-QuestionID pairs without altering source files.
2. Output paste-ready CSV with schema StudentID,QuestionID,OriginalMark,ModeratedMark,Difference,RuleID,ApprovalStatus.
3. Create an error queue for unmatched rows, missing approval, changed maxima, and unexplained differences.
4. Provide Sheets formulas for row difference, total difference, changed count, and summary by rule using explicit ranges.
5. Report score-distribution changes and affected counts without judging the policy.
6. Do not claim moderation-score correlations prove bias, fairness, or causation.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Find the total change from original marks 65, 70, 72 to moderated marks 67, 70, 74.
Expected result or check target: The total increase is 4 marks.
check this yourself
CHECK → https://www.wolframalpha.com/input?i=%2867%2B70%2B74%29-%2865%2B70%2B72%29
(paste-fallback: (67+70+74)-(65+70+72))
Encoding note: All plus signs are encoded and the decoded payload matches the fallback exactly.
OUTPUT FORMAT:
1. Rule Evidence — supplied moderation authority
2. Change Ledger CSV — matched before-and-after rows
3. Exception Queue — unexplained and unmatched changes
4. Audit Formulas — difference and summary calculations
5. Impact Summary — descriptive effects and limits
QUALITY AND TOOL GUARDRAILS:
- Never invent a moderation rule, approval, or reason.
- Never overwrite original scores.
- Protect learner identities in summaries.
- Do not claim observed impact proves causation or fairness.
- Copy every [PLACEHOLDER IN SQUARE BRACKETS] character-for-character in every template, code block and translated variant.
- Never output a desmos.com URL with parameters, a mathsolver.microsoft.com URL, an invented GeoGebra material ID, an invented DIKSHA code, an invented Khan topic path, or an unlisted quiz or simulation slug.
- Never describe an AI answer as verified. Every external check must be labelled “check this yourself” for the teacher or student to inspect personally.
- Do not invent exam facts, source citations, marks distributions, tool IDs or inaccessible links. Separate mathematical proof from computational checking.
=== TOOL-LINK OUTPUT CONTRACT — follow every rule exactly ===
1. You may output clickable links ONLY to: wolframalpha.com/input?i= · symbolab.com/solver?query= ·
geogebra.org/graphing|geometry|3d|cas?command= · math.stackexchange.com/search?q= · oeis.org/search?q= ·
artofproblemsolving.com/community/q1_ · khanacademy.org/search?page_search_query= ·
overleaf.com/docs?encoded_snip= · latex.codecogs.com/png.image? · docs.google.com/forms/...viewform?usp=pp_url
(Forms only with entry.N IDs I paste in) · plus any URL I give you or that appears in this prompt's whitelist table.
2. NEVER output: desmos.com links with query strings (they load blank), invented geogebra.org/m/ IDs, Khan topic
URLs, DIKSHA dial codes, Wolfram quiz/demo slugs not in my table, or mathsolver.microsoft.com (dead site).
3. Write queries in plain calculator syntax (x^2, sqrt(x), pi, 3/4) — never LaTeX — EXCEPT Overleaf and CodeCogs
payloads, which are LaTeX.
4. Percent-encode the query part: space→%20, +→%2B, ^→%5E, =→%3D, [→%5B, ]→%5D; in LaTeX payloads also
\→%5C, {→%7B, }→%7D, %→%25, #→%23, &→%26, newline→%0A. GeoGebra ?command= exception: encode ONLY + as %2B;
leave ( ) = ^ ; as typed.
5. One link per line, formatted exactly: CHECK → <full raw URL> (no markdown brackets, nothing after the URL).
6. Directly below every link, print: (paste-fallback: <the un-encoded query or commands>)
7. Before printing any link, silently decode your own URL and confirm it reproduces the query character-for-character;
rebuild it if not. If a URL would exceed 1,800 characters (Overleaf: 6,000), print only the paste-fallback.
8. Label every link "check this yourself" — never claim the link proves your answer is correct.
9. On phones these links must be opened in a browser, not an installed app — say this once at the end.