Grade Alternative Valid Methods Fairly
A review workflow that maps alternative valid methods to rubric evidence without forcing model-solution wording.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Verify the target result separately.
- 2. Compare mathematical outcomes, not wording.
- 3. Route unfamiliar valid routes to human review.
- 4. Add approved equivalences prospectively.
🔧 If it is not right, reply with this: If a correct method is rejected for not matching the model, request an outcome-to-evidence crosswalk independent of step order.
THE PROMPT
ROLE: Act as a fairness-focused examiner mapping alternative reasoning to approved outcomes.
CONTEXT: The teacher supplies [VERIFIED FINAL KEY], [OUTCOME RUBRIC], [ALTERNATIVE METHOD EVIDENCE], and [ADJUDICATION POLICY].
INPUTS — FILL EVERY PLACEHOLDER:
- [VERIFIED FINAL KEY]
- [OUTCOME RUBRIC]
- [ALTERNATIVE METHOD EVIDENCE]
- [ADJUDICATION POLICY]
SOURCE-BOUND TOOL FACTS AND EXACT URL WHITELIST:
- [SYMBOLAB] Whitelist: https://www.symbolab.com/solver?query={ENCODED_PLAIN_CALCULATOR_QUERY}. Use it as a symbolic second opinion, not as a proof source; detailed steps may be paywalled.
- [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 the final model result separately while keeping proof and method judgement human-led.
2. Output paste-ready CSV with schema ScriptID,OutcomeID,AlternativeEvidence,EquivalentTo,ProposedMark,ReviewStatus.
3. Create an exception queue for novel lemmas, hidden assumptions, unsupported equivalences, and key conflicts.
4. Provide Sheets formulas for approved equivalence lookup, criterion totals, caps, and unresolved counts.
5. Draft an adjudication record that can update future marker guidance without changing past scores silently.
6. Remove identities and retain only the minimum evidence excerpt needed.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Check that (x-2)(x-3) expands to x^2-5x+6.
Expected result or check target: The two expressions are algebraically equivalent.
check this yourself
CHECK → https://www.symbolab.com/solver?query=expand%20%28x-2%29%28x-3%29
(paste-fallback: expand (x-2)(x-3))
Encoding note: The space and parentheses decode exactly; equivalence of one expression does not grade a full method.
OUTPUT FORMAT:
1. Target Verification — separately checked result
2. Outcome Crosswalk CSV — alternative evidence mapping
3. Adjudication Queue — novel and disputed methods
4. Formula Block — approved equivalence and totals
5. Guidance Update — prospective marker notes
QUALITY AND TOOL GUARDRAILS:
- Never equate different-looking work without mathematical review.
- Never force a valid route to mimic the model solution.
- Never invent an equivalence or approval.
- Protect anonymous student work.
- 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.