With new tools leveraging GenAI testing capabilities emerging, how should we evaluate the trade-offs between adopting such tools versus building our own internal frameworks tailored to our needs? The concern is reg. vendor lock, etc.,
Could you please suggest a roadmap for someone with over 10 years of experience in manual testing, including how AI can be incorporated to enhance career growth, and whether gaining automation skills is necessary?
The Claude to be associated with tools from MCP servers it requires the upgraded version of Claude. Is it not possible to integrate the MCP with free version of claude?
Do QA specialists need coding + AI/ML knowledge, or is domain expertise plus AI tools enough?
What are the new testing topics to be required to validate any copilot or chatbot or LLM powered software ?
Do you think AI will ever be able to truly reason like humans, or will it always be advanced pattern matching?
How does prompt engineering and domain knowledge helpful in AI journey?
How should testers balance between test automation frameworks and AI-driven test platforms?
In my company we are building AI use cases where developers create multiple AI agents. As a QA, could you please suggest the right strategy, tools, or any of your courses that would help me learn how to validate AI agents effectively ?
If we don’t fully understand how AI works internally, what does it mean to have “AI-driven” testing or software development?
Do you think AI will create entirely new career paths in testing that don’t exist today? If yes, what might they look like?
Is MCP server used when working on real world automation project in a IT company?
How is the impact of AI different for UI and Data testing disciplines?
What’s your take on AI-powered automation tools in the market?
What’s your advice for someone who wants to follow your path in teaching?
Are we still need to recheck manually after we do automation test?
How do you maintain work-life balance?
What is your approach on testing AI systems (e.g. testing model inference, etc) ?
In RAGAS We have testsetgenerator for generating test data set in question answer format.
But For that we need to store those files on our local and provide the documents path.
How to handle if I am having 700+ documents as parts of RAG System.?
With so many AI tools available, how can one select the right tool that truly fits their needs? Are there any ground rules or breakthrough thoughts you’d recommend for making that choice?