AI Prompt Engineering for Testers, Performance Pyramid and More

For the past month I’ve been focusing on our annual online Automation Testing event Automation Guild that took place last week. Now that it’s over I wanted to create a quickrecap of some news items you might have missed over the past few weeks.

Leverage the power of Generative AI in the testing world.

First, I had the pleasure of catching up with two of my favorite automation testing tool entrepreneurs, Guy Arieli and Tal Barmeir and they told me all about what they see as a perfect use of Generative AI with automation.

So, they showed me their latest creation, Blinq.io, and they went over how it can help prompt engineering in the testing world, leveraging Cucumber's feature files to get AI working for you in your tests. And due to Generative AI, prompt engineering is gaining traction. You've probably heard a lot about it, and this innovative approach involves integrating artificial intelligence into the testing process, mainly through using Cucumber feature files, a tool used in behavior-driven development. And like anything, the key to harnessing AI's potential in testing lies in effective communication between the testing process and the AI system. So, prompt engineering is the heart of this integration.

This innovative solution uses Cucumber to help testers and automation engineers create prompts and directives with Cucumber feature files that an AI system can understand. These prompts can instruct AI to perform various tasks like generating test cases, prioritizing scenarios, and helping identify risk areas, or they can enable you to execute tests automatically under many changing conditions. I like this approach because it creates a direct bridge between traditional testing practices and the advanced capabilities of AI, and it allows testing teams to enhance efforts with AI-driven insights and actions. The result is a more innovative, more adaptive testing process that combines the expertise of a human tester that will always be needed with the efficiency of AI, leading to improved efficiency and, hopefully, software quality. ?????? Try it for yourself now and see how it works, and then let me know your thoughts in the comments below.

King of AI

Last week I also had a great conversation on my podcast with the King of AI Tariq King who peeled back the layers of the validation vs. verification debate and explore insights into the meteoric rise of generative AI and ChatGPT, challenging our preconceived notions and expectations of AI's role in testing. He shared his enthusiasm for the unexpected surge in adoption among testers, a trend that even took him by surprise.

Tariq also dissects the intricacies of human-AI collaboration, how AI is redefining but not replacing human work, and the criticality of human insight in developing truly transformative AI systems. From multi-modal AI to language and image interpretation integration, we're looking at the future of UI-level automation. So listen in as Tariq King gives us a no-nonsense guide to AI in testing automation.

Get Instant Access to Automation Guild 2024?

Obviously, AI was a big topic at this year’s Automation Guild, and we had a lot of great sessions around this topic and other top automation topics.

If you missed it, you could still get a ticket and get instant access to all the recordings that took place during the event. Plus, you’ll be able to join our community and upskill all year long with with our new continual monthly training session planned for March-November.

Performance Testing Pyramid?

Also did you check out the new performance testing model I mentioned in the last news show from my friends Leandro Melendez (Se?or Performo) and Federico Toledo?

This performance model obviously was inspired by the famous Cohn Pyramid for functional automated tests and is designed to optimize performance testing strategies and agile software development. And this pyramid model for performance testing emphasizes the importance of automating various types of software tests including load tests, which are crucial for preparing systems for high-demand scenarios, and this model also helps in understanding how systems behave under heavy concurrent user access preventing potential performance issues. This pyramid stands as a guide for defining a performance testing strategy, particularly in systems with microservices. It provides a detailed look at each layer of the pyramid from unit performance testing to client-side performance, offering insights into the advantages and disadvantages of each.

Thats a Wrap

Ok, I wanted to keep this quick but stay tuned for the latest and greatest when we drop a new news episode on Monday.

As always, test everything and keep the good - Cheers!

?