Building Better Agents: Evaluation Frameworks & Feedback Loops for Automated Improvement

​Join us at the Google office in Chicago for a special evening focused on building and improving LLM-powered agents.

As developers push the boundaries of what agents can do, a key challenge emerges: how do you evaluate performance, identify failure modes, and enable agents to improve over time—autonomously? In this session, we’ll explore practical strategies for tracing agent behavior, running structured evaluations, optimizing prompts, and closing the loop with experimentation and monitoring.
Whether you're building with open-source frameworks or rolling your own, you’ll leave with actionable techniques and ideas to level up your agentic systems.

Come for the technical deep dive, stay for the food, drinks, and great conversations with fellow builders.

Event Agenda

​5:30 PM – 6:30 PM - Check-In & Networking

​6:30 PM – 6:45 PM - Welcome Remarks - Opening the evening with a brief introduction to the event, speakers, and key themes.

​6:45 PM – 7:00 PM - Google Cloud AI Factory
An overview of Google Cloud’s AI Factory and how it supports scalable and efficient AI development.

​7:00 PM – 7:15 PM - Feedback-Driven Agent Development with Arize AI
SallyAnn DeLucia, Arize AI - Discover how feedback loops are transforming agent performance and reliability in production environments.

​7:15 PM – 7:45 PM
Panel: Exploring AI Agents in the Enterprise — Use Cases, Challenges, and What’s Next - Neda Hantehzadeh (CCC Intelligent Solutions), Robert Montgomery (Tempus Labs), Jason Lopatecki (Arize AI)- A discussion on how enterprises are adopting agentic systems, the hurdles they face, and the future of agent-enabled AI applications.

**A valid government issued ID is required for entry.