Artificial Intelligence Machine Learning

The Fellowship of Agentic Evaluations: How to Evaluate an Agent?

FORMAT: WorkshopLEVEL: Intermediate LANGUAGE: Spanish

How do you know if your AI agent is actually doing the right thing? In this workshop, we'll explore practical evaluation frameworks for agentic systems. Forming a fellowship of evaluation techniques—from simple unit tests to complex behavioral evaluations—we'll apply them to real agent scenarios. You'll learn to define evaluation criteria, implement automated test suites, measure agent performance quantitatively, and track improvement over time.

Speakers

María Fernanda Rojas Castro

ML Engineer @ Loka

María Fernanda is an ML Engineer at Loka with expertise in building and evaluating intelligent systems. She focuses on practical methodologies for ensuring AI agent reliability and safety, and collaborates on research into scalable evaluation techniques for production agentic workflows.

View speaker

Nicolás Roldán Fajardo

ML Engineer @ Loka

Nicolás is an ML Engineer at Loka focused on evaluation frameworks for agentic AI systems. He works on designing robust test suites that validate agent behavior across complex multi-step workflows, bringing engineering rigor to the often-overlooked challenge of AI evaluation.

View speaker

Want to know more?

Join PyCon Colombia newsletter and get a complete overview of our events, speakers and community participation.