Build an Assessment Dashboard Input Pack
A validated set of fact and dimension CSV blocks, formulas, and refresh checks for a teacher-owned dashboard.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Keep raw, cleaned, and summary tabs separate.
- 2. Use stable anonymous keys.
- 3. Resolve every orphan lookup row.
- 4. Refresh formulas after each new export.
🔧 If it is not right, reply with this: If dashboard totals disagree, request source-to-summary reconciliation by row count, maximum marks, and score sum.
THE PROMPT
ROLE: Act as a data-model designer preparing auditable assessment inputs for Google Sheets.
CONTEXT: The teacher supplies [RAW EXPORTS], [STUDENT LOOKUP], [QUESTION LOOKUP], and [DASHBOARD METRICS].
INPUTS — FILL EVERY PLACEHOLDER:
- [RAW EXPORTS]
- [STUDENT LOOKUP]
- [QUESTION LOOKUP]
- [DASHBOARD METRICS]
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. Define fact-table and lookup-table keys before transforming any rows.
2. Output paste-ready CSV blocks with schemas Responses(StudentID,AssessmentID,QuestionID,Mark,Status), Students(StudentID,Group), and Questions(QuestionID,Topic,MaxMark).
3. Create a validation queue for duplicate keys, orphan IDs, invalid marks, blanks, and conflicting lookup values.
4. Provide Sheets formulas with explicit columns and first/last rows for reconciliation counts, sums, and selected dashboard metrics.
5. Add a refresh checklist comparing raw rows, accepted rows, rejected rows, and total marks.
6. Keep interpretations descriptive and never claim dashboard correlations prove causation.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Reconcile 120 raw rows as 115 accepted plus 5 rejected rows.
Expected result or check target: The accepted and rejected rows sum to all 120 raw rows.
check this yourself
CHECK → https://www.wolframalpha.com/input?i=115%2B5
(paste-fallback: 115+5)
Encoding note: The plus sign is encoded as %2B and decodes to the exact reconciliation fallback.
OUTPUT FORMAT:
1. Data Model — fact and dimension keys
2. CSV Pack — rectangular paste-ready tables
3. Validation Queue — rejected and orphan records
4. Formula Pack — dashboard and reconciliation formulas
5. Refresh Checklist — repeatable quality controls
QUALITY AND TOOL GUARDRAILS:
- Never invent lookup values, group labels, or metrics.
- Never merge raw and cleaned data destructively.
- Minimise personal data and keep IDs anonymous.
- Do not claim dashboard correlations prove 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.