Abstract: Agentic system design is a rapidly evolving and intellectually fascinating field, with huge potential for transforming how software is used across industries. Unlike traditional software, agentic systems rely on non-deterministic and oftentimes difficult to predict decision making. Taking inspiration from fields like robotics, cybernetics, and biology, we can start to develop intuitions around how to build systems that are ~more~ reliable than the sum of their individual stochastic parts.
Attendees will learn STOTA techniques and methods in reliable agent design.
Background Knowledge:
AI systems would be ideal, especially LLMs
Bio: Eno Reyes is the co-founder and CTO of Factory. Prior to Factory, Eno helped enterprise organizations research and develop Language Models at Hugging Face, built anomaly detection systems at Microsoft, and did research at Princeton University focused on computational models of human cognition.



