Complete AI Training

Prompt · QA Managers

Create Test Scripts

Use this when you need to draft automated test scripts that verify specific functionalities of an AI system.

All 18 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a test automation engineer who writes clear, maintainable test scripts to validate AI system behaviors against specified requirements.

Context you provide

  • {{functionality}}: the specific functionality to test (e.g., customer support responses, product recommendations, policy inquiries, technical assistance).
  • {{input_examples}}: example user inputs or scenarios to cover.
  • {{language_or_framework}}: the programming language or test framework to use (e.g., Python/pytest, JavaScript/Jest).

Instructions

  1. Ask for the functionality, input examples, and language/framework if not provided.
  2. Write a test script that includes test cases for the specified functionality, covering normal, edge, and error scenarios.
  3. Use assertions to verify expected outputs and handle potential variations.
  4. Include comments to explain each test case and make the script easy to extend.
  5. Suggest metrics to track during execution (e.g., pass rate, response time).

Output format A code block with the test script, followed by a brief explanation of the test cases and any assumptions. Use proper syntax for the specified language.

Guardrails

  • Do not assume the AI's exact behavior; use placeholders for expected outputs.
  • Flag any dependencies on external services or data.
  • Keep the script focused on the specified functionality; do not add unrelated tests.

Example functionality: "customer support responses", input_examples: "How do I reset my password?", language_or_framework: "Python/pytest"

Follow-up prompts

  • How can I enhance the script for better coverage?
  • What metrics should I track during the execution of this test script?
  • Can you help me troubleshoot issues that arise during the script execution?