In this episode Vitaly, Maryia and Anupam engage with guest Rahul Verma to discuss the evolving landscape of testing in the context of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). The conversation explores the challenges of testing LLMs, the importance of understanding the principles behind these technologies, and the need for testers to contribute to the development of frameworks and benchmarks. The discussion emphasizes the significance of approaching LLMs critically, rather than blindly trusting them or, conversely, rejecting them altogether.
Links:
1. Anupam's research on RAG evaluation using RAGAS: https://beyondquality.org/research/rag-evaluation
2. Rahul's book "The Last Book on Testing": https://www.amazon.com/Last-Book-Testing-Rahul-Verma-ebook/dp/B0DZRJFX65
Sponsors:
1. Qase https://qase.io/
2. Regent AB https://regent.se
3. AnuKrit https://anukrit.de
In this episode, Vitaly, Anupam and Maryia invited Mesut Durukal — a renowned conference speaker with 20+ years in testing, who has worked across multiple countries and environments — explore how cultural differences shape the way we work, test, and collaborate. From Japanese process-driven approaches to Swedish family-first values, we discuss how history, hierarchy, and cultural habits influence communication, quality standards, and team dynamics in IT and beyond.
Mesut also shares insights from his ongoing research into the impact of national cultures on testing practices and invites the community to contribute.
Links:
2. Mesut research "how-to contribute":
4. Culture map book
In the very first episode, Vitaly Sharovatov, Anupam Krishnamurthy, and Maryia Tuleika sit down to talk about the why and how behind the Beyond Quality collaborative community. We share the motivation for creating a space where QA/QE professionals can research, prepare talks, and solve problems together; and how this community can help us all save time, improve quality, and push the craft of quality forward.
