Separate Accuracy From Attempt Rate
A two-axis question report distinguishing willingness to attempt from success among attempts.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Define an attempt consistently.
- 2. Exclude absences by policy.
- 3. Show numerator and denominator for both rates.
- 4. Choose interventions separately for access and accuracy.
🔧 If it is not right, reply with this: If accuracy is calculated over the whole class, ask for correct divided by attempted and attempt divided by eligible as separate formulas.
THE PROMPT
ROLE: Act as an item analyst separating participation from correctness.
CONTEXT: The teacher supplies [ITEM STATUS CSV], [ATTEMPT DEFINITION], [ELIGIBILITY POLICY], and [QUESTION TOPIC MAP].
INPUTS — FILL EVERY PLACEHOLDER:
- [ITEM STATUS CSV]
- [ATTEMPT DEFINITION]
- [ELIGIBILITY POLICY]
- [QUESTION TOPIC MAP]
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 status values and preserve eligible, attempted, correct, wrong, and blank distinctions.
2. Output paste-ready CSV with schema StudentID,QuestionID,Topic,Eligible,Attempted,Correct.
3. Create an error queue for impossible combinations, unknown statuses, duplicates, and missing topics.
4. Provide Sheets formulas for attempt rate and accuracy among attempts with explicit columns and row limits.
5. Place questions in a teacher-readable high-low quadrant using supplied thresholds only.
6. Do not claim the relationship between attempt and accuracy proves confidence, motivation, or causal barriers.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Compute accuracy when 21 of 28 attempts are correct.
Expected result or check target: Accuracy among attempts is 75 percent.
check this yourself
CHECK → https://www.wolframalpha.com/input?i=%2821%2F28%29%2A100
(paste-fallback: (21/28)*100)
Encoding note: The encoded expression decodes exactly; the attempt rate uses a different denominator.
OUTPUT FORMAT:
1. Status Rules — attempt and eligibility definitions
2. Item Status CSV — validated binary fields
3. Logic Error Queue — impossible and missing states
4. Rate Formulas — separate denominators
5. Quadrant Actions — teacher review suggestions
QUALITY AND TOOL GUARDRAILS:
- Never equate blank with wrong without the supplied definition.
- Never invent quadrant thresholds.
- Keep response-level identities private.
- Do not claim attempt-accuracy 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.