Building Better AI Agents: Evaluation Frameworks for Success

As AI agents become more advanced and widely adopted, the ability to evaluate their performance is crucial for driving meaningful improvements, enhancing reliability, and ensuring real-world impact. This event brings together experts from leading organizations, including Google, Arize AI, Autogen, DeepMind, and Weaviate, to share insights, tools, and strategies for building and optimizing next-generation agentic systems.
Join us for an evening of engaging tech talks and discussions as we explore:

• Evaluation techniques for understanding and improving agent performance in dynamic, real-world environments.
• Strategies for optimising agentic AI systems to ensure robustness, autonomy, and decision-making efficiency.
• The importance of guardrails and reliability in building scalable AI applications.
• Real-world applications and case studies from the frontlines of AI system development.

This is a must-attend event for developers, engineers, and AI practitioners looking to deepen their expertise in evaluating and optimizing AI agents.

🥂 Enjoy complimentary food, drinks, and fun event swag!

Agenda:

• 5:30-6:30 PM - Check-in & Networking
• 6:30-6:50 PM - Building Reliable Agent Systems with Google Cloud
• Speaker: Bruno Hesse, EMEA Head and MD of ISV Ecosystem, Google
• 6:50-7:10 PM - Evaluating AI Agent Behaviors with Arize AI
• Speaker: Jason Lopatecki, Co-Founder & CEO, Arize AI
• 7:10-7:30 PM - Optimising Agentic AI Systems with AutoGen
• Speaker: Chi Wang, Founder, AutoGen
• 7:30-7:50 PM - Guardrails in Agentic RAG with Weaviate
• Speaker: Deepti Naidu, Solution Engineer, Weaviate
• 7:50-8:10 PM - Q&A Session
• 8:10-9:00 PM - Networking & Wrap-Up