By the end of this chapter, learners will be able to:
- Use prompt engineering to generate, debug, and explain code
- Solve mathematical and logical problems through structured prompts
- Analyze data, generate summaries, and simulate SQL or spreadsheet logic
- Leverage prompt styles specific to technical tasks with high accuracy

Language models can assist with:
- Writing and explaining code
- Solving mathematical equations
- Debugging logic
- Simulating database queries
- Creating data summaries and visualizations
Prompt engineering ensures technical outputs are accurate, structured, and complete.

Basic Code Generation

Prompt:
"Write a Python function to check if a number is a palindrome."
Output:

def is_palindrome(n):
    return str(n) == str(n)[::-1]

✅ Use precise language: "function", "Python", "return Boolean"

Multistep Instruction

Prompt:
"Write a Python script that reads a CSV file, filters rows where age > 30, and saves the output."
Use delimiters for long code:

# script goes here

Debugging and Fixes

Prompt:
"Fix this error in JavaScript code:

let x = [1, 2, 3];
console.log(x[3].toUpperCase());

Explain the error."
Output:
"x[3] is undefined, so calling toUpperCase() throws an error."

Prompt:
"Explain the following C++ code line-by-line to a beginner:

for (int i = 0; i < 10; i++) { cout << i; }

You can also define the audience:
- "Explain to a beginner"
- "Explain like I’m a senior engineer reviewing it"

Prompt styles that work well:
- Chain-of-thought prompting: "Solve step by step"
- Specify format: "Give final answer in bold"
Prompt Example:

"If x + 3 = 10, what is the value of x? Show your steps."
Output:
1. x + 3 = 10
2. Subtract 3 from both sides: x = 7
3. Answer: 7

Language models can mimic SQL or spreadsheet logic.
Prompt:

"Write a SQL query to get the top 5 highest paid employees from a table named employees with columns name, salary.
Output:

SELECT name, salary
FROM employees
ORDER BY salary DESC
LIMIT 5;

Excel Formulas

Prompt:
"Create an Excel formula to calculate the average sales in cells B2 to B10, ignoring blank cells."
Output:

=AVERAGEIF(B2:B10, "<>")

VLOOKUP Explanation

Prompt:
"Explain how to use VLOOKUP to match a student ID with a name from another sheet."

Prompt:
"Summarize this data:
Product A: 40 units sold
Product B: 75 units sold
Product C: 25 units sold"
Output:
"Product B had the highest sales, followed by A and C. Total units sold: 140."

✅ Be explicit about language "Use Python" or "Write in R" avoids ambiguity
✅ Use delimiters Keeps code readable and reduces misinterpretation
✅ Ask for explanation Enhances learning, especially for beginners
✅ Define input/output "Function should take a list and return a sorted version"
✅ Use test cases "Add 2 test cases at the end of the code"

Limitation Prompt Strategy
Truncating long code Break into parts, use streaming/step-by-step prompts
Output formatting issues Request Markdown or use triple backticks
Mistakes in logic/math Use "Think step-by-step" or request error checks
Complex queries not executing Ask for explanation with query

Prompt engineering helps AI handle technical tasks like coding, math, and data analysis with higher accuracy and structure. By providing clear intent, language, format, and structure, you can use AI as a code assistant, data analyst, or math tutor.