Automating Testing in the Age of Large Language Models - Tapa blanda

Sinopsis

AI is changing software development, and QA is right in the middle of it.

Large language models can generate test cases, write automation code, analyze failures, create test data, explore requirements, and even interact with testing environments. But using AI effectively in QA is not as simple as asking a chatbot to "write some tests."

The real challenge is knowing where AI actually helps, where it creates new problems, and where a human QA engineer still needs to be firmly in control.

Practical AI for QA Engineers is a hands-on guide for QA engineers, automation engineers, SDETs, and software testers who want to use AI as part of their everyday testing work without falling into the hype.

The book starts with the fundamentals of large language models and explains what makes AI-assisted testing different from traditional automation. From there, it moves into practical applications that you can use in real projects.

You'll learn how to use AI to:

• Analyze requirements and discover missing test scenarios
• Generate and improve test cases
• Write better prompts for QA work
• Create API and UI automation
• Generate realistic test data
• Investigate and debug automation failures
• Improve bug reports and technical documentation
• Work with AI during exploratory testing
• Refactor and maintain existing automation
• Use AI in CI/CD and continuous testing
• Manage test environments and application state
• Build more reliable AI-assisted QA workflows
• Understand AI agents and autonomous testing
• Evaluate the risks of over-automation
• Decide what should—and should not—be delegated to AI

The book also looks at the less comfortable side of AI.

AI-generated tests can be repetitive. AI can confidently produce incorrect assumptions. Automated failure analysis can misclassify real defects as "flaky tests." More automation can create more maintenance instead of better coverage.

These are not theoretical concerns. They are practical problems QA engineers need to understand before putting AI into production workflows.

Throughout the book, the focus stays on engineering judgment rather than AI hype. The examples show how AI can become part of an existing QA process instead of trying to replace the process entirely.

You'll see realistic scenarios involving requirements, automation, APIs, CI pipelines, test data, environments, flaky tests, and failure investigation. The goal isn't to create the biggest possible test suite. It's to create better evidence about software quality with less unnecessary work.

Most importantly, this book explores how the QA role itself is changing.

As AI becomes better at writing code and generating tests, knowing how to type automation code becomes less valuable on its own. Understanding risk, system behavior, test architecture, failure analysis, and the right questions to ask becomes more important.

This book is for you if:

• You are a QA or automation engineer who wants to start using AI seriously
• You already use ChatGPT or other AI tools but want a more structured approach
• You write UI, API, or end-to-end automation
• You want practical ideas rather than another book about AI hype
• You want to understand AI agents and autonomous testing
• You are wondering how AI will affect the QA engineering role
• You want to become more productive without blindly trusting AI-generated output

AI will change how testing is done.

The question isn't whether QA engineers should use it.

The better question is:

How can you use AI to become a better QA engineer without giving up the engineering judgment that makes good testing possible?

This book is about answering that question.

"Sinopsis" puede pertenecer a otra edición de este libro.