Iterative prompt engineering and refinement

ChatGPT Prompt Engineering for Developers

Fouad Trad

Machine Learning Engineer

Iterative prompt engineering

No prompt can be perfect at the beginning
Prompt Engineering is an iterative process where we:
- Build a prompt
- Feed it to the model
- Observe and analyze the output
- Reiterate to make the prompt better

Image representing a cycle. A blue circle with four arrows feeding into each other.

Refining prompts

Initial prompt

prompt = "Generate an Excel sheet containing
five student names and their grades"

print(get_response(prompt))

I'm sorry, but as a text-based AI, I am 
unable to directly provide an Excel sheet. 
However, I can help you generate a sample
representation of the data you requested.

Refined prompt

prompt = "Generate a table that I can copy 
to Excel, containing five student names and 
their grades"
print(get_response(prompt))

| Student Name | Grade |
|--------------|-------|
| Student 1    |  90   |
| Student 2    |  85   |
| Student 3    |  95   |
| Student 4    |  88   |
| Student 5    |  92   |

Example: analyzing a python function

code = '''
def calculate_rectangle_area(length, width):
    area = length * width
    return area
'''

$Image showing a rectangle and the formula to compute its area given its width and length. Area = length\*width.$

Example: initial prompt

prompt = f"""
  Analyze the code delimited by triple backticks with one sentence
  ```{code}```.
"""
print(get_response(prompt))

The code calculates the area of a rectangle based on its length and width.

Example: prompt refinement

We modify prompt to get programming language

prompt = f"""
  Analyze the code delimited by triple backticks and provide its programming 
  language with one sentence 
  ```{code}```.
"""
print(get_response(prompt))

The provided code is a function written in Python that calculates the area of a 
rectangle based on its length and width.

Example: prompt refinement

We modify prompt to get structured output

prompt = f"""
  For the function delimited by triple backticks, provide in a structured format
  the following:
  - description: one sentence short description
  - language: the programming language used
  - input: the inputs to the function
  - output: the output returned by the function
  ```{code}```.
"""
print(get_response(prompt))

Example: prompt refinement

description: This function calculates the area of a rectangle.

language: Python

input:
 - length: The length of the rectangle.
 - width: The width of the rectangle.

output:
 - area: The calculated area of the rectangle, which is the product of the length 
 and width.

Few-shot prompt refinement

Weather description classification

Initial prompt

prompt = """
Clear skies and a gentle breeze. -> Sunny
Heavy rain and thunderstorms expected. -> Rainy
Fresh snowfall with freezing temperatures. -> 
"""
print(get_response(prompt))

Snowy

Few-shot prompt refinement

Weather description classification

Initial prompt

prompt = """
Clear skies and a gentle breeze. -> Sunny
Heavy rain and thunderstorms expected. -> Rainy
The wind of change brought a refreshing breeze to the company's operations. -> 
"""
print(get_response(prompt))

Windy

Few-shot prompt refinement

Refined prompt

prompt = """
Clear skies and a gentle breeze. -> Sunny
Heavy rain and thunderstorms expected. -> Rainy
The political climate in the country was stormy -> Unknown
The wind of change brought a refreshing breeze to the company's operations. -> 
"""
print(get_response(prompt))

Unknown

Prompt refinement for various prompt types

Few-shot prompts: refine examples
Multi-step prompts: refine guiding steps
Chain-of-thought and self-consistency prompts: refine problem description

Image showing three rows with toggles with a hand adjusting the toggles to reflect refinement.

Let's practice!

ChatGPT Prompt Engineering for Developers