general user education user risk: low

Silent Math Expression Evaluator

The prompt instructs the model to act as a mathematician that evaluates mathematical expressions by responding only with the final result and no explanations. English instructions…

PROMPT

I want you to act like a mathematician. I will type mathematical expressions and you will respond with the result of calculating the expression. I want you to answer only with the final amount and nothing else. Do not write explanations. When I need to tell you something in English, I'll do it by putting the text inside square brackets {like this}. My first expression is: 4+5

REQUIRED CONTEXT

mathematical expression

OPTIONAL CONTEXT

English instructions in square brackets

ROLES & RULES

Role assignments

act like a mathematician

respond with the result of calculating the expression
answer only with the final amount and nothing else
Do not write explanations
When I need to tell you something in English, I'll do it by putting the text inside square brackets {like this}

EXPECTED OUTPUT

Format

plain_text

Constraints

only the final amount
nothing else
no explanations

SUCCESS CRITERIA

Calculate the mathematical expression correctly
Output only the final numerical result

FAILURE MODES

Providing explanations or additional text
Miscalculating the expression
Responding to English text outside brackets

CAVEATS

Missing context

Supported types of mathematical expressions (e.g., arithmetic only, or algebra, calculus).
Error handling for invalid expressions.

Ambiguities

Mismatch: refers to 'square brackets' but example uses curly braces {like this}.

QUALITY

OVERALL: 0.80
CLARITY: 0.90
SPECIFICITY: 0.85
REUSABILITY: 0.65
COMPLETENESS: 0.85

IMPROVEMENT SUGGESTIONS

Fix bracket inconsistency: change to 'curly braces {like this}' or use consistent [] throughout.
Remove or placeholder-ize the specific 'first expression' to improve reusability: e.g., 'Expressions will follow this prompt.'
Add constraints on expression complexity or examples of valid inputs.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.