AI for Software Testers: Apply AI Tools and Techniques to the Software Testing Life Cycle

Course details

Software testing is often the most repetitive aspect of a large software project, with many similar tests, customized slightly for different contexts, and then constant evaluation of those test results. AI coding techniques can simplify these intensive test review cycles. Instructor Mchael Smith walks you through the possibilities, from using AI to help you decide on testing targets and strategies through implementing them with ChatGPT, GitHub Copilot, and similar tools, as well as evaluating test reports.

Learning objectives
Explore the range of AI tools available to software testers.
Apply AI tools to planning and ideation, as well as evaluating plans.
Generate comprehensive test suites at a variety of levels for complex program development.
Use GitHub Copilot and ChatGPT to fill gaps in coding for testing.
Create dashboards and reports to display the results of your testing.

Concepts

0. Introduction

01 - Using AI for software testing
02 - What you should know
03 - Ethical considerations in AI-assisted testing

1. Introduction to AI in Software Testing

04 - Why AI matters for testers
05 - Overview of AI tools for testers
06 - Setting up AI tools
07 - Additional tools

2. AI for Test Case Generation

08 - Using ChatGPT for test case ideation
09 - Creating test scenarios from requirements using Gemini
10 - Enhancing code quality with GitHub Copilot
11 - Generating framework templates with AI

3. AI for Automated Testing

12 - Writing automation scripts with GitHub Copilot
13 - Debugging code with AI
14 - Dashboarding automated testing results using AI

4. AI in Test Data and Reporting

15 - Generating test data with ChatGPT and synthetic data
16 - Summarizing test results with ChatGPT
17 - Analyzing defects in GitHub Copilot

Conclusion

18 - Next steps

AI for Software Testers: Apply AI Tools and Techniques to the Software Testing Life Cycle

Authors

Mike Smith