GenAI, specifically the Large Language Models, are the new shiny thing. Like others, testers are also amused by this new technology. Alas, most such amusement is confined to shallow experiments and those too confined to raw prompting at the web GUI interface layer for the said models like ChatGPT. Of course, the results seen by most testers are superficial accordingly. Many such testers become disinterested in the LLMs because of this experience, although a deeper look could have changed their minds.
This talk explores many more opportunities with the discussion based on The 5E Model for using LLMs in testing, developed by Rahul Verma. LLMs, with the inherent limitations of non-determinism and other flaws, can still be put to practical use in many activities in testing. The 5E model helps in thinking about LLMs right from a simple start to the very complex organisational situations.
Talk Takeaways
Rahul Verma is an awarded thought leader for his contributions to the testing community. He is a Senior Coach and Consultant with trendig technology services gmbh. He is the creator of Swayam – an LLM framework for layered prompting and Arjuna – a free, open-source Python based modern test automation framework. He is a contributing author and reviewer for various certification bodies including Artificial Intelligence United, Selenium United, ISTQB and CMAP.
His software testing experience includes using Large Language Models in testing, building test automation frameworks in Python, web security, white box testing and web performance testing. His research work focuses on exploring meta-programming and object oriented design patterns as applied to automating activities in all these areas.
He has presented, published articles and educated thousands of testers in the said areas. His testing ideas and work are deeply influenced by his deep interest in poetry and spirituality.
