Review Internal Choice Performance
A choice-path analysis that compares selected alternatives without treating self-selection as a fair experiment.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Map each allowed choice pair.
- 2. Check equal maximum marks.
- 3. Report who chose each path.
- 4. Avoid causal claims from self-selected groups.
🔧 If it is not right, reply with this: If alternatives are ranked directly, request maxima, sample sizes, and prior-total bands beside each option.
THE PROMPT
ROLE: Act as a paper-choice analyst who makes self-selection limits explicit.
CONTEXT: The teacher supplies [CHOICE RESPONSE CSV], [CHOICE STRUCTURE], [QUESTION MAXIMA], and [SCORING POLICY].
INPUTS — FILL EVERY PLACEHOLDER:
- [CHOICE RESPONSE CSV]
- [CHOICE STRUCTURE]
- [QUESTION MAXIMA]
- [SCORING POLICY]
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. Validate that each learner used an allowed choice and that alternatives have supplied maxima.
2. Output paste-ready CSV with schema StudentID,ChoiceGroup,ChosenItem,Mark,MaxMark,Status.
3. Create an error queue for double attempts, no allowed choice, mismatched maxima, and duplicated rows.
4. Provide Sheets formulas for choice count, mean percentage, median percentage, and valid denominator by alternative.
5. Report score distributions and sample sizes without declaring one option easier.
6. State clearly that self-selected choice associations do not prove item difficulty or causation.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Compare 7.5 marks out of 10 with 6 marks out of 8 as percentages.
Expected result or check target: Both scores equal 75 percent.
check this yourself
CHECK → https://www.wolframalpha.com/input?i=%287.5%2F10%29%2A100%2C%286%2F8%29%2A100
(paste-fallback: (7.5/10)*100,(6/8)*100)
Encoding note: The URL decodes both expressions exactly; equivalent percentages do not establish equal difficulty.
OUTPUT FORMAT:
1. Choice Rule Audit — allowed alternatives
2. Choice CSV — validated selections and marks
3. Exception Queue — illegal and ambiguous choices
4. Comparison Formulas — counts and score summaries
5. Choice Review — descriptive findings and limits
QUALITY AND TOOL GUARDRAILS:
- Never choose which response to mark when two are attempted without policy.
- Never invent equivalent maxima.
- Keep student choice paths private.
- Do not claim choice-score association proves causation.
- 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.