Department of Computational and Data Sciences
Department Seminar
Speaker : Yam Marcovitz, Tech Lead, PARLANT.IO, Israel
Title : “Agentic AI Framework ”
Date & Time: June 6th, 2025 (Friday), 04:00 PM
Venue : # 102, CDS Seminar Hall
ABSTRACT
Building AI that can handle customer conversations effectively has been hyped up to be a simple problem, but in practice, it’s one of the most complex challenges in modern AI. Large language models often struggle with consistency, attention drift, and subtle (yet crucial) errors. And while conversations are often repetitive in intent, real users behave unpredictably, rarely choosing to follow scripted “happy paths.” Drawing from real-world experience, this talk explores why truly fluid and reliable conversational AI remains a practical moonshot—and the technical reasons why getting it right is far harder than it seems.
BIO: Formerly a software architect at Microsoft and Apex.AI, Yam brings a unique combination of deep technical expertise and systems thinking to AI development. With extensive experience in high-performance computing and system architecture, including building real-time systems with microsecond-level precision for autonomous vehicles, Yam understands what it takes to create reliable, production-grade software. This background informs his distinctive approach to AI development in Parlant, an open-source framework that fundamentally reimagines how we control AI agent behavior.
Host Faculty: Dr. Yogesh Simmhan
ALL ARE WELCOME
