A Very Testing Chat: Testing OpenAI's ChatGPT | TTC Global

A Very Testing Chat: Testing OpenAI's ChatGPT

Abilities and Limitations for Developing a Testing Workflow

Web Zander
  • Zander Von Neudegg
  • 13 February 2023

I am not here to sell you on a new AI cult or to tell you that this new chat bot will change your life, but there is a reason ChatGPT is the fastest adopted internet application in history. Yes, media has overhyped it, it is not perfect, and it’s certainly not sentient, but it is useful and evolving quickly. Below is a conversation I had with ChatGPT to display some of its abilities and limitations specifically regarding a testing workflow. For full transparency, a few of these below prompts were regenerated to better keep the conversation flowing, however this is indicative of how I truly use the tool. It’s a dance, going back and forth – but I believe it is a tango worth learning if you want to keep a competitive edge in today’s market. These are the topics that I discussed with ChatGPT and actions I requested it to perform:

  • Use cases of ChatGPT for Automation Testing
  • Cucumber test case for testing a Login Page
  • Supporting Java Selenium code behind it
  • Encrypting the password using AES encryption algorithm
  • Use cases for Manual Testing
  • How to improve Everyday Workflows beyond software testing

Automation Testing (Response by ChatGPT)

ChatGPT has many potential use cases in automation testing, which is the process of automating the execution of test cases to validate software functionality. Here are a few ways that ChatGPT can be used in automation testing.

  1. Test Case Generation: ChatGPT can be used to generate test cases based on requirements of a software application. By understanding the content and the requirements, ChatGPT can generate test cases that cover all of the necessary scenarios and edge cases. This can significantly reduce the time and effort required to manually write test cases.
  2. Test Data Generation: ChatGPT can also be used to generate test data for software applications. Test data is an essential component of automation testing, and ChatGPT's ability to generate human-like text can be used to generate realistic test data for various use cases.
  3. Test Result Analysis: ChatGPT can also be used to analyse test results. It can extract relevant information from the test results and summarize it in a concise manner, making it easier for testers to understand the results and identify areas for improvement.
  4. Bug Reporting: ChatGPT can be used to generate reports based on the test results. It can extract relevant information from the test results and generate a detailed bug report that includes steps to reproduce the bug, expected behaviors, and actual behavior.

In conclusion, ChatGPT has many potential use cases in automation testing, and it can significantly reduce the time and effort required to perform various tasks. It's ability to understand and generate human-like text makes it a valuable tool for streamlining testing processes and improving the efficiency of automation testing.

Manual Testing (Response by ChatGPT):

  1. Test Case Generation: ChatGPT can be used to generate test cases based on a given set of requirements. This can be particularly useful for creating test cases for large and complex systems.
  2. Test Plan Creation: ChatGPT can be used to generate a comprehensive test plan for a given system, including the scope of testing, test objectives, and the test cases to be executed.
  3. Test Data Generation: ChatGPT can be used to generate test data for manual testing, including input data for functional testing and edge cases for negative testing.
  4. Test Execution: ChatGPT can assist manual testers by providing step by step instructions for executing tests and documenting test results.
  5. Defect Reporting: ChatGPT can be used to generate bug reports based on the test results and provide suggestions for potential root causes.
  6. Test Case Maintenance: ChatGPT can be used to maintain and update test cases as changes are made to the system being tested, reducing the effort required to keep test cases up to date.

Overall, ChatGPT can significantly streamline manual testing by automating repetitive and time-consuming tasks, freeing up manual testers to focus on more critical and creative tasks.

Everyday Workflows (Response by ChatGPT):

ChatGPT can also be used to improve everyday workflows beyond just software testing. Here are a few examples:

  1. Email and Document Composition: ChatGPT can be used to generate emails, reports, and other written documents, reducing the time and effort required to compose them.
  2. Data Analysis and Reporting: ChatGPT can be used to extract insights from large datasets, automate data analysis, and generate reports and visualizations.
  3. Customer Service: ChatGPT can be used to handle customer inquiries and support requests, freeing up human agents to focus on more complex and critical tasks.
  4. Virtual Personal Assistant: ChatGPT can be used as a virtual personal assistant, performing tasks such as scheduling appointments, managing email, and providing reminders.
  5. Content Generation: ChatGPT can be used to generate content for websites, social media, and marketing materials, saving time and effort for marketers and content creators.

These are just a few examples of how ChatGPT can be integrated into everyday workflows to improve efficiency and productivity. The possibilities are virtually endless, and the technology is constantly evolving, providing even more opportunities for integration in the future.

Read the Full Conversation with ChatGPT: