How to beginner · 3 min read

How to prompt AI for code generation

Quick answer

To prompt AI for code generation, use clear, specific instructions including the programming language, desired functionality, and any constraints. Include example inputs and expected outputs in your prompt to improve accuracy and relevance.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install openai>=1.0

Setup

Install the openai Python package and set your API key as an environment variable for secure access.

bash

pip install openai>=1.0

Step by step

Use the OpenAI SDK to send a detailed prompt specifying the programming language, task, and example inputs/outputs. This example generates a Python function to reverse a string.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

prompt_text = (
    "Write a Python function named <code>reverse_string</code> that takes a string and returns it reversed."
    " Include example input: 'hello' and expected output: 'olleh'."
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": prompt_text}]
)

print(response.choices[0].message.content)

output

def reverse_string(s):
    return s[::-1]

Common variations

You can use other models like claude-3-5-sonnet-20241022 with Anthropic's SDK or enable streaming for real-time code generation. Adjust prompts to specify language or style.

python

import os
import anthropic

client = anthropic.Anthropic(api_key=os.environ["ANTHROPIC_API_KEY"])

system_prompt = "You are a helpful assistant that writes Python code."
user_prompt = (
    "Create a Python function <code>factorial</code> that returns the factorial of a number."
    " Provide example input 5 and output 120."
)

message = client.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=200,
    system=system_prompt,
    messages=[{"role": "user", "content": user_prompt}]
)

print(message.content[0].text)

output

def factorial(n):
    if n == 0:
        return 1
    else:
        return n * factorial(n-1)

Troubleshooting

If the generated code is incomplete or incorrect, refine your prompt by adding more examples or clarifying requirements. Also, verify your API key and model name are correct to avoid authentication or model errors.

✅

Key Takeaways

Specify the programming language and function purpose clearly in your prompt.
Include example inputs and expected outputs to guide the AI.
Use the latest SDK patterns with environment variables for API keys.
Experiment with different models and prompt styles for best results.

Verified 2026-04 · gpt-4o, claude-3-5-sonnet-20241022

Verify ↗