How to beginner · 3 min read

How to prompt AI to write unit tests

Quick answer

To prompt AI to write unit tests, provide the source code or function signature along with clear instructions specifying the testing framework and test cases you want. Use explicit prompts like Write unit tests in Python using unittest for this function to get precise, runnable test code.

PREREQUISITES

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

Setup

Install the OpenAI Python SDK and set your API key as an environment variable to authenticate requests.

bash

pip install openai>=1.0

Step by step

Use the OpenAI SDK to send a prompt that includes the function code and a clear instruction to generate unit tests using unittest. The example below demonstrates a complete runnable script.

python

import os
from openai import OpenAI

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

function_code = '''
def add(a, b):
    """Return the sum of a and b."""
    return a + b
'''

prompt = f"""Write Python unit tests using unittest for the following function:\n{function_code}"""

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

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

output

import unittest

class TestAddFunction(unittest.TestCase):
    def test_add_positive_numbers(self):
        self.assertEqual(add(2, 3), 5)

    def test_add_negative_numbers(self):
        self.assertEqual(add(-1, -1), -2)

    def test_add_zero(self):
        self.assertEqual(add(0, 0), 0)

if __name__ == '__main__':
    unittest.main()

Common variations

You can prompt for different testing frameworks like pytest, request async test functions, or use other models such as claude-3-5-haiku-20241022. Adjust the prompt accordingly.

python

import os
import anthropic

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

function_code = '''
async def fetch_data(url):
    """Fetch data asynchronously from a URL."""
    pass
'''

prompt = f"""Write async unit tests using pytest-asyncio for this function:\n{function_code}"""

message = client.messages.create(
    model="claude-3-5-haiku-20241022",
    max_tokens=1024,
    system="You are a helpful assistant.",
    messages=[{"role": "user", "content": prompt}]
)

print(message.content[0].text)

output

# Example output with async pytest tests for fetch_data function

Troubleshooting

If the AI generates incomplete or incorrect tests, refine your prompt by specifying the expected input-output pairs, edge cases, and the testing framework explicitly. Also, verify your API key and model name to avoid authentication or model errors.

Key Takeaways

Always include the function code and specify the testing framework in your prompt for accurate unit tests.
Use the latest SDK patterns and environment variables for secure and reliable API calls.
Customize prompts to request async tests or different frameworks like pytest for varied testing needs.

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

Verify ↗

Community Notes

No notes yetBe the first to share a version-specific fix or tip.