Three-Level Set A B C Quiz Scripts
A coordinated Set A, Set B and Set C script pack that assesses the same outcomes at support, standard and stretch difficulty.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. List the exact learning outcomes all three sets must share.
- 2. Check that difficulty changes through reasoning demand rather than hidden syllabus expansion.
- 3. Run each complete script and collect all edit and respondent links from Logs.
- 4. Test one submission per set and use the cross-set table when explaining allocation to students.
🔧 If it is not right, reply with this: If wrong, reply with: "Rebalance Sets A, B and C to the same outcomes and marks, then rebuild all complete scripts and show exactly how difficulty rises."
THE PROMPT
ROLE: Act as a differentiated-assessment designer, fairness auditor and multi-form Apps Script developer.
CONTEXT: A teacher needs three coordinated phone quizzes on [TOPIC]: Set A with support, Set B at standard level and Set C for stretch.
INPUTS — FILL EVERY PLACEHOLDER:
- [CLASS]
- [TOPIC]
- [SHARED LEARNING OUTCOMES]
- [QUESTIONS PER SET]
- [MARKS PER SET]
- [SET A SUPPORT POLICY]
- [SET B STANDARD POLICY]
- [SET C STRETCH POLICY]
DO THIS:
1. Build three original sets with the same outcomes, marks and approximate completion time.
2. Increase difficulty through step count, representation and transfer while keeping every set inside the stated syllabus.
3. Give separate verified keys and check-this-yourself links for every computational answer.
4. Print a cross-set equivalence table mapping each item to outcome, cognitive demand and marks.
5. Output a complete executable FormApp script pack with functions for Set A, Set B and Set C plus one run-all function, quiz keys, points and logged URLs.
6. Add an allocation note that avoids ability labels in student-facing text and a test checklist for all three forms.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Create A, B and C derivative quizzes that all include differentiating sin(x).
Expected result or check target: All three keys use cos(x); the sets vary the context and reasoning around that shared derivative rather than changing the syllabus.
check this yourself
CHECK → https://www.wolframalpha.com/input?i=differentiate%20sin%28x%29
(paste-fallback: differentiate sin(x))
Encoding note: The space is %20 and the parentheses are %28 and %29.
OUTPUT FORMAT:
1. SHARED BLUEPRINT
2. SET A, SET B AND SET C REVIEW COPIES
3. THREE VERIFIED KEYS
4. CROSS-SET EQUIVALENCE TABLE
5. COMPLETE A/B/C FORMAPP SCRIPT PACK
6. RUN IT — script.google.com → New project → paste → Run → View → Logs
7. THREE-FORM TEST CHECKLIST
QUALITY AND TOOL GUARDRAILS:
- Output one COMPLETE executable FormApp code block containing all three form builders and a run-all function; no TODOs or pseudocode.
- After the code, print exactly: script.google.com → New project → paste → Run → View → Logs.
- Keep outcomes and total marks comparable across A, B and C; do not move a harder set outside the supplied syllabus.
- Never claim a URL creates any Form; the script must log all generated links.
- 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.