Welcome to episode 15 of the Why Didn’t You Test That? Podcast! In this episode, Curiosity's Rich Jordan and James Walker, are joined by Mark Winteringham, author of "AI-Assisted Testing". Together they reflect on their experience with AI, the effect it has had on software quality and testing, and the future of AI Co-Pilots.
LLMs, namely ChatGPT, Gemini and Llama are cool, but what do they offer in terms of delivering software quality? What leaps have you taken in using generative AI technology? How will you future-proof your AI-Assisted testing efforts? By now you really should be considering these questions at a strategic organisational level.
Guest Mark Winteringham unravels a collage of challenges as he reflects on his new book "AI Assisted Testing” with our hosts. Providing a balanced perspective in understanding the progress, plateaus, and benefits of using artificial intelligence and co-pilots for delivering quality software.
James follows up by exploring the value of AI Co-Pilots in testing and the importance of context in prompt engineering, emphasising the need for experimentation to determine what actually makes a good prompt.
Seen with a healthy scepticism, prompts can be used as aids to extend quality testing abilities. But to yield better results, rather than prompting AI with a broad question, the advice is to target specific parts of the system or problem.
What does implementing AI technology in to your SDLC actually mean, and how does it work? The possibilities seem endless, and large language model’s keep growing, but has there been an impact, is true transformational change still a while away?
Watch the complete episode to find out!
%20copy.png?width=29&height=35&name=file-document-multiple%20(1)%20copy.png){kind=small}
