AI Agent Evaluation: Techniques for Building Better Agentic Systems

As AI agents become increasingly sophisticated, evaluating their performance is essential for driving meaningful improvements and ensuring reliability in real-world applications. Join us for an in-depth exploration of AI agent evaluation, where experts from Google, Arize, LlamaIndex, and others working on the emerging AI agent & assistants tech stack will share advanced techniques for building and optimizing agentic systems.

This event will delve into evaluation methodologies, engineering learnings from the trenches, and the latest research focused on the nuanced behaviors of AI agents in dynamic environments.

Through a series of tech talks from Google, Arize, LlamaIndex, Priceline, AutoGen and Weaviate, we’ll explore:

• Advanced evaluation techniques for AI agents, focusing on real-world performance metrics.
• Key methods for optimizing agentic systems to improve decision-making, autonomy, and robustness.
• The latest tools and frameworks used in agent development and system evaluation.

Discover best practices for iterating on agent behavior through continuous evaluation and feedback loops

🥂 Complimentary food and drinks will be provided!