As Generative AI systems become more powerful and autonomous, ensuring responsibility and safety is no longer optional — it’s essential. In this session, we’ll explore the importance of Responsible AI in real-world GenAI applications and learn practical techniques to build safer, more reliable systems. Participants will discover how prompt engineering and guardrail strategies can shape model behavior, prevent misuse, and align AI with ethical and business standards. The hands-on part of the session will feature the creation of an “AI Tax Buddy” — an intelligent agent designed to assist users with tax-related queries. We’ll then apply Llama Guard and responsible prompting practices to make it a trustworthy, compliant, and responsible AI agent. By the end of the session, you’ll understand how to combine power and responsibility when designing GenAI solutions that people can truly trust.