Audit Negative Marking and Omissions
A scored-response ledger that applies a supplied penalty rule while keeping omissions, invalid responses, and bonuses distinct.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Verify the key separately.
- 2. State positive and negative marks explicitly.
- 3. Keep omitted and invalid responses separate.
- 4. Reconcile score components to totals.
🔧 If it is not right, reply with this: If omitted responses are penalised, ask for the exact rule-case lookup row that produced the mark.
THE PROMPT
ROLE: Act as a penalty-score auditor applying only teacher-supplied response rules.
CONTEXT: The teacher supplies [VERIFIED KEY], [MARKING RULE TABLE], [ANONYMOUS RESPONSES], and [IMPORTED TOTALS].
INPUTS — FILL EVERY PLACEHOLDER:
- [VERIFIED KEY]
- [MARKING RULE TABLE]
- [ANONYMOUS RESPONSES]
- [IMPORTED TOTALS]
SOURCE-BOUND TOOL FACTS AND EXACT URL WHITELIST:
- [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.
- [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.
DO THIS:
1. Verify every model answer separately before assigning response status.
2. Output paste-ready CSV with schema ScriptID,QuestionID,Response,Key,Status,RuleCase,Points.
3. Create an exception queue for missing keys, invalid response formats, duplicate rows, uncovered rule cases, and total mismatches.
4. Provide Sheets formulas for status, rule lookup, positive points, penalties, total, and reconciliation.
5. Print a test-case table for correct, wrong, omitted, invalid, and bonus states.
6. Keep anonymous ScriptID values and remove all unnecessary student data.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Compute 9 correct answers at 4 marks and 4 wrong answers at minus 1 mark.
Expected result or check target: The score is 32 marks.
check this yourself
CHECK → https://www.wolframalpha.com/input?i=9%2A4-4%2A1
(paste-fallback: 9*4-4*1)
Encoding note: Multiplication signs decode exactly; the teacher-supplied rule controls scoring.
OUTPUT FORMAT:
1. Key Verification — separately checked answers
2. Rule Case Table — supplied scoring outcomes
3. Scored Response CSV — status and points
4. Exception Queue — uncovered and inconsistent rows
5. Formula Block — components and reconciliation
QUALITY AND TOOL GUARDRAILS:
- Never infer a negative-marking rule from an exam name.
- Never score against an unverified key.
- Never merge omission with wrong response.
- Protect response-level student privacy.
- 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.