Diagnose Blank Versus Wrong Responses
A response-status analysis separating omission, attempted error, not-reached, and absence before any intervention is suggested.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Preserve the original response text.
- 2. Define each status code before analysis.
- 3. Separate not-reached from deliberate omission.
- 4. Review patterns with classroom evidence.
🔧 If it is not right, reply with this: If blank cells are all counted as wrong, require an explicit status column and recompute every denominator.
THE PROMPT
ROLE: Act as an assessment-diagnostic analyst distinguishing missingness from incorrect work.
CONTEXT: The teacher supplies [RAW RESPONSE CSV], [STATUS CODEBOOK], [QUESTION ORDER], and [ABSENCE RULE].
INPUTS — FILL EVERY PLACEHOLDER:
- [RAW RESPONSE CSV]
- [STATUS CODEBOOK]
- [QUESTION ORDER]
- [ABSENCE RULE]
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. Keep the original response and supplied status in separate fields.
2. Output paste-ready CSV with schema StudentID,QuestionID,Response,Status,Correctness,QuestionOrder.
3. Create a validation queue for empty status codes, unknown codes, duplicate responses, and absent learners with marks.
4. Provide Sheets formulas for blank rate, wrong-among-attempted rate, not-reached rate, and valid denominator.
5. Compare late-paper omissions with earlier omissions while reporting counts and uncertainty.
6. Describe patterns as associations and never claim they prove time pressure, motivation, or understanding.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Compute the blank rate when 12 of 40 eligible responses are blank.
Expected result or check target: The blank rate is 0.3, or 30 percent.
check this yourself
CHECK → https://www.wolframalpha.com/input?i=12%2F40
(paste-fallback: 12/40)
Encoding note: The slash decodes exactly; eligibility still follows the supplied absence rule.
OUTPUT FORMAT:
1. Status Codebook — teacher-supplied definitions
2. Response CSV — preserved text and classifications
3. Validation Queue — ambiguous missingness
4. Formula Block — status-specific rates
5. Diagnostic Table — cautious question-order patterns
QUALITY AND TOOL GUARDRAILS:
- Never convert an unclassified blank to zero automatically.
- Never infer motivation from an omitted response.
- Protect response text and anonymous IDs.
- Do not claim association with question order 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.