User-centricity for AI-assisted Test Engineers

Traditional software testing is fundamentally deterministic: the same inputs must always produce the same outputs. Yet many teams introduce AI into their testing without first defining the problem the AI is meant to solve, leading to brute-force experimentation and unreliable results. Google’s 2025 DORA report highlights that user-centricity is a prerequisite for AI success and that AI is most effective when it is pointed at a clear problem. AP shows you how that insight applies technically to testing. Before AI can be used as a testing tool, it must first be tested and understood in the context of the specific problem it is meant to address. Join Aprajita Mathur as she takes you through a journey of what she has learned while testing bioinformatics models and how to apply these learning to AI models in your testing workflows. She will share her approach of a refined deterministic middle layer. Instead of testing raw model behavior, you can apply basic engineering principles and define structured contracts, schemas, models, and constraints that make AI outputs testable, repeatable, and auditable. She will share examples in this session to demonstrate how engineering discipline transforms AI from a probabilistic assistant into a reliable component of modern test automation. You will learn how to point AI at the right problem!