AI isn't just changing test automation. It's changing Quality Engineering.

For years, the goal of test automation was simple: execute more tests.

Today, the challenge is different.

With AI, we can identify high-risk areas, uncover missing test scenarios, analyze failures faster, and help teams focus their efforts where it matters most.

But how do you apply this in practice?

I've been using tools like Claude, ChatGPT, and Gemini as part of my QA workflow.

Here are a few examples:

• Paste a User Story and ask the AI to identify test scenarios that might have been overlooked.
• Share a Pull Request and ask for a risk analysis, including which features could be impacted by the changes.
• After a production issue, provide the error logs and ask the AI to suggest possible root causes and which automated tests could have prevented the problem.
• Before closing a sprint, ask the AI to review your test suite and identify gaps in coverage.

These prompts take only a few minutes, but they often reveal issues that would be missed during a traditional review.

In my opinion, the next evolution of Quality Engineering isn't about creating more tests.

It's about using AI to make better engineering decisions.

How are you using AI in your QA process? Or are you still using it mainly to generate code?