Name
GenAI in the Hot Seat: Halting Hallucinations & Securing AI
Description
Get ready to put your GenAI systems on trial and integrate top-notch evaluation methods right into your CI/CD pipeline! In this fast-paced, hands-on workshop, you'll dive deep into Evaluation Driven Development for GenAI solutions. We'll cover everything from nipping hallucinations in the bud to securing your systems and embedding evaluation seamlessly into your continuous integration and deployment process. Whether you're a developer, product designer, or AI enthusiast, join us for an interactive session that provides a streamlined toolkit to ensure your GenAI solutions not only perform but excel in a high-stakes, fast-moving environment.
Speakers
Date & Time
Wednesday, July 30, 2025, 2:00 PM - 3:15 PM
Location Name
Crest 3
Session Type
Workshop
Track
What are some recent technical innovations to help me, my team & my organization improve?
Learning Objectives
Understand the Fundamentals: Grasp the core principles of evaluation-driven development and its critical role in GenAI systems.
Design Robust Evaluations: Learn how to create effective evaluation criteria and testing frameworks that address the unique challenges of GenAI, including strategies to minimize hallucinations.
Integrate with CI/CD: Discover how to embed your evaluation processes into your CI/CD pipeline, ensuring continuous quality assurance and rapid deployment cycles.
Enhance Security Practices: Identify and apply security evaluation strategies to protect your GenAI solutions from vulnerabilities.
Measure What Matters: Track and measure key performance metrics to ensure your AI solutions meet both functional and ethical standards.
Hands-On Application: Engage in practical exercises and real-world scenarios to immediately apply these concepts, preparing you to implement these practices in your own projects.
Design Robust Evaluations: Learn how to create effective evaluation criteria and testing frameworks that address the unique challenges of GenAI, including strategies to minimize hallucinations.
Integrate with CI/CD: Discover how to embed your evaluation processes into your CI/CD pipeline, ensuring continuous quality assurance and rapid deployment cycles.
Enhance Security Practices: Identify and apply security evaluation strategies to protect your GenAI solutions from vulnerabilities.
Measure What Matters: Track and measure key performance metrics to ensure your AI solutions meet both functional and ethical standards.
Hands-On Application: Engage in practical exercises and real-world scenarios to immediately apply these concepts, preparing you to implement these practices in your own projects.