When Software Starts Thinking: The Now of Quality Engineering

For decades, Quality Engineering has been built around a simple rule: given the same input, software produces the same output. Generative AI has fundamentally changed that.

Large Language Model based applications, Retrieval-Augmented Generation (RAG) systems and AI agents don't behave like traditional software. They reason, adapt, use memory, invoke tools and collaborate with other agents. The result is a new class of enterprise applications where correctness is no longer binary, and traditional testing techniques alone are no longer enough.

In this session, I'll explore how Quality Engineering must evolve into AI Assurance — a discipline focused on building confidence in AI systems rather than simply verifying functionality.

Using practical examples from enterprise AI implementations, we'll examine the new challenges AI introduces: evaluating non-deterministic outputs, validating RAG pipelines, measuring hallucinations, testing autonomous agent workflows, securing AI against prompt injection, and defining meaningful quality metrics beyond pass/fail test cases.

This talk presents a practical way of thinking about quality in AI-powered products. We'll discuss how concepts such as trust, risk, observability, governance and continuous evaluation are becoming as important as automation and regression testing.

Attendees will leave with a clear understanding of why AI systems require a different engineering mindset, how existing QE practices can evolve instead of being replaced, and what skills quality engineers need as AI agents become an integral part of enterprise software.

If your next product includes an LLM, an AI copilot or an autonomous agent, this session will help you rethink what "quality" really means.