2025-11-05 –, Eng
Talking about AI agents is easy, but building ones that actually work is very hard.
In this talk, I’ll introduce the concept of AI agents and outline key implementation challenges—compound errors, business context, and high cost and latency. I’ll share a practical framework for building agents, including core components, planning strategies, and evaluation methods, and show how we at AI21 Labs apply these to develop effective, reliable agent-based products.
Talking about AI agents is easy, but building ones that actually work is very hard.
In this talk, I will briefly introduce the concept of AI agents and highlight three major challenges in their implementation: compound errors, business context and their high cost and latency.
I will present a general framework for developing AI agents, covering essential components, planning strategies, and evaluation methodologies.
Finally, I will discuss how we at AI21 Labs apply these approaches to create agent-based products that are both effective and reliable.
No previous knowledge expected
Shuki Cohen is an AI Evangelist at AI21 Labs, on a mission to make Artificial Intelligence more accessible, understandable, and impactful for anyone curious about its potential. AI21 Labs is pioneering the development of enterprise AI systems and foundation models, turning cutting-edge research into enterprise-grade AI solutions built for the agentic future.
With an M.Sc. in Industrial Engineering, specializing in Data Science from Tel Aviv University, Shuki brings a strong technical foundation and a passion for sharing the power of AI through clear, engaging and crisp takeaways.