AI Tool Face Off!

Feeling overwhelmed by the sheer volume of AI tools promising to revolutionize quality assurance? Cut through the noise in this practical session designed to help you and your team identify which AI assistants actually deliver value for software testing. Brian will dive into a side-by-side comparison of GitHub Copilot, Google Gemini, and Claude Code across essential daily QA workflows: generating test cases directly from pull request changes and specification documents, constructing comprehensive test plans for new features, and asking strategic testing questions—such as how to approach mobile app camera testing or when to choose physical devices over simulators. Rather than relying on marketing hype, you will observe how each tool performs on identical, realistic testing scenarios, revealing where they excel, where they fall short, and how practical their responses are in practice. By attending this session, attendees will walk away with a clear understanding of the unique strengths of Copilot, Gemini, and Claude Code, a practical framework for evaluating AI tools against your team's specific QA workflows, and actionable strategies to boost test coverage and efficiency without wasting time on trial and error.