Speakers

Manoj is a seasoned professional and adept technologist. He enjoys exploring the entire software development lifecycle and is especially interested in solving problems in Software Quality, Digital Transformation, Human-Computer Interaction, and Cloud Computing spaces. Having worked in enterprises, Fintech, and early-stage startups for over 15 years, Manoj brings a wealth of experience. Notably, he is a contributor to the Selenium project and serves on the project leadership committee for Selenium. He genuinely believes that sharing knowledge and experiences strengthens our community. Manoj is a member and Distinguished Speaker of the ACM and IEEE Computer Society. He has given keynote addresses and technical talks at numerous international conferences on software engineering and testing in over 12 countries. Manoj has previously worked at startups like Applitools and LambdaTest and has been a part of digital transformation programs at leading companies such as ThoughtWorks, Wipro, and IAG, among others.

The AI Leap in Test Automation: Harnessing LLMs and Multimodal Capabilities

Imagine a world where your test automation framework is not only efficient but also intelligent, adaptive, and capable of handling multimodal inputs effortlessly. Welcome to a new era in test automation, where the power of Generative AI and Large Language Models (LLMs) like GPT revolutionise our approach to quality assurance.

In this talk, I’ll break down the complexities of LLMs and generative AI. We’ll embark on a journey through these cutting-edge technologies, exploring how they can transform our approach to testing. We’ll delve into the concepts of prompt engineering, the integration of multimodal capabilities, and their application in real-world test automation scenarios. You’ll see how GPT and similar generative AI models can enhance automation by understanding and generating human-like text, handling diverse input types, and offering predictive insights. We’ll also discuss the integration of multimodal LLMs, which combine text, images, and other data types to provide a richer, more comprehensive testing environment.

To bring theory into practice, we’ll showcase a live demo of integrating multimodal LLMs with Selenium, highlighting the practical and future potential of these innovations.