W5 Embracing the Fuzzy: Testing in the Age of Generative AI

As generative AI becomes increasingly integrated into software products, traditional testing approaches often fall short in handling the unique challenges these systems present, such as unpredictability, biases, and misinformation risks. This full-day workshop dives into testing strategies tailored for generative AI.

Through a blend of instruction, interactive discussions, and practical exercises, participants will learn to test the complexities of inexplicable fuzzy AI that carries context-dependent risks.

Attendees will gain insights and experience in: Risk Analysis: Recognize and assess AI-specific risks inherent to generative models Testing Strategies: Develop test approaches that accommodate the fuzzy nature of AI Benchmarking: Develop methods to evaluate both functional performance and safety This workshop is designed for software developers, testers, quality assurance professionals, and product managers desiring to responsibly and effectively integrate generative AI into their software.

Ben Simo

Ben SimoBen Simo is an inveterate software quality expert with decades of experience advancing exploratory testing, test automation, and performance evaluation across industries ranging from healthcare to e-commerce.

As a Principal Product Researcher at Tricentis, he is pioneering methods for testing AI systems and leveraging AI to empower testers. A frequent speaker at global conferences, Ben is known for his deep technical insight, hands-on problem-solving, and commitment to improving the quality and observability of complex software systems. He is known on social media by his handle Quality Frog.