Predict Before the Graph Reveals
A tightly scripted predict-vote-reveal-explain routine built around one exact GeoGebra visual and a common misconception.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Paste the concept and the misconception you hear most often.
- 2. Check the expected graph values before class.
- 3. Ask the prediction with the link still closed.
- 4. Record student votes and reasons before revealing the visual.
- 5. End with an explanation students can write without referring to the picture.
🔧 If it is not right, reply with this: If wrong, reply with: “Make the prediction answerable before the reveal, show the exact counterexample values, and rebuild the link around one misconception.”
THE PROMPT
ROLE: You are a formative-assessment designer who uses a delayed visual reveal to surface and repair one mathematical misconception.
CONTEXT: Class [CLASS] is studying [CONCEPT], and the reveal must confront [LIKELY MISCONCEPTION] using [FUNCTION OR FIGURE].
INPUTS — FILL EVERY PLACEHOLDER:
- [CLASS]
- [BOARD OR EXAM]
- [CONCEPT]
- [LIKELY MISCONCEPTION]
- [FUNCTION OR FIGURE]
- [REVEAL FEATURE]
DO THIS:
1. Write one prediction with two plausible alternatives and require a reason, not a guess.
2. Calculate the exact values that will settle the prediction.
3. Build one GeoGebra link that opens with the decisive graph or construction already present.
4. Specify a reveal order that starts with the unannotated idea and ends with the decisive feature.
5. Give raw commands and a hand-drawn fallback.
6. Create a transfer question that uses new numbers but the same reasoning.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Ask whether adding a positive constant to x^2 moves its roots outward, inward, or removes them, then reveal a=1 in g(x)=x^2+a.
Expected result or check target: Students vote before a slider-controlled parabola opens with its roots and vertex, allowing the a=1 no-real-root case to settle the claim.
check this yourself
CHECK → https://www.geogebra.org/graphing?command=f(x)=x^2;a=1;g(x)=f(x)%2Ba;Root(g);Extremum(g)
(paste-fallback: f(x)=x^2;a=1;g(x)=f(x)+a;Root(g);Extremum(g))
Encoding note: The vertical-shift addition is encoded as %2B; parentheses, equals signs, carets, and semicolons remain literal.
OUTPUT FORMAT:
1. PREDICTION — two choices plus a reason prompt
2. EXPECTED VALUES — the teacher's private check
3. ONE-CLICK REVEAL LINK — labelled check this yourself
4. PASTE FALLBACK — unencoded commands
5. REVEAL SCRIPT — vote, show, notice, explain
6. TRANSFER QUESTION — same concept, new case
QUALITY AND TOOL GUARDRAILS:
- Use only an allowed GeoGebra ?command= endpoint and no invented /m/ ID.
- Use at most 12 commands; encode every + as %2B and keep ()=^; literal.
- Never include a Desmos URL; a Desmos fallback, if useful, must be typed lines only.
- Never use mathsolver.microsoft.com or let the image substitute for a mathematical explanation.
- 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.