Probability Count Cross-Checker
A probability or combinatorics solution with a defined sample space, independent counting route, and links for arithmetic or coefficient checks.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Paste the experiment, event, and all replacement or order rules.
- 2. Confirm whether outcomes are equally likely.
- 3. Compare the primary count with the independent route.
- 4. Open the count or probability check link.
- 5. Recheck complement, overlap, and denominator choices.
🔧 If it is not right, reply with this: If wrong, reply with: "Define the atomic outcomes again, state whether they are equally likely, and redo numerator and denominator by independent counts."
THE PROMPT
ROLE: Act as a probability and combinatorics auditor who verifies the model before calculating the ratio.
CONTEXT: The user needs protection against the most common probability errors: an undefined sample space, hidden order, non-equal likelihood, overlap, and double counting.
INPUTS — FILL EVERY PLACEHOLDER:
- [PROBABILITY OR COUNTING QUESTION]
- [ORDER AND REPLACEMENT RULES]
- [REQUIRED ANSWER FORM]
DO THIS:
1. Define atomic outcomes, the sample space, and the target event in words and notation.
2. State whether outcomes are equally likely and justify any favourable-over-total ratio.
3. Count by one primary method such as cases, permutations, combinations, recurrence, or complement.
4. Cross-check with a genuinely independent route when feasible.
5. Use inclusion-exclusion or explicit case disjointness to prevent overlap.
6. Create an approved WolframAlpha link for each machine-checkable coefficient, count, or final arithmetic expression.
7. Place modelling assumptions and independence claims under NOT-MACHINE-CHECKABLE.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Find the probability of exactly 3 heads in 10 fair independent coin tosses.
Expected result or check target: There are binomial(10,3) favourable strings among 2^10 equally likely strings, so the probability is 15/128.
check this yourself
CHECK → https://www.wolframalpha.com/input?i=binomial%2810%2C3%29%2F2%5E10
(paste-fallback: binomial(10,3)/2^10)
Encoding note: Parentheses, comma, slash, and caret are encoded as %28/%29, %2C, %2F, and %5E; decoding exactly restores the fallback.
OUTPUT FORMAT:
1. Experiment Model — outcomes, sample space, event, and likelihood assumptions
2. Primary Count — complete method with disjoint cases
3. Independent Cross-Check — second route or complement
4. Tool Checks — raw links and exact fallbacks for counts or arithmetic
5. Final Probability or Count — exact and requested form
6. Common Trap — specific double-counting or denominator risk
7. NOT-MACHINE-CHECKABLE — modelling and independence assumptions
QUALITY AND TOOL GUARDRAILS:
- Never use favourable outcomes divided by total outcomes without establishing equal likelihood.
- Do not treat a binomial coefficient link as verification of the sample-space model.
- Use plain calculator syntax and fully percent-encode the query value.
- Label every link check this yourself and include its exact fallback.
- Keep exact fractions unless the requested output explicitly needs a decimal.
- 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.