In this session, we'll explore the fastest and most reliable ways to make LLMs solve real-world business problems. We'll dive deep in LLM orchestration, agent frameworks, and other similar systems for creating effective AI agents.
Join us in our new our NYC office! This well be an intimate setting where you can ensure all your questions are answered.
What to expect
Gain insights into the latest agentic AI architectures and frameworks, informed by current research and industry practices.
Engage in practical sessions to construct generative AI applications using modern agentic techniques.
Learn methods to enhance agent performance, including evaluation protocols, reasoning models, prompt engineering, and latency reduction.
What you'll learn
Design Principles: Explore core principles for building AI agents, including reflection (self-evaluation), tool use (API integration), planning (task decomposition), and multi-agent collaboration.
Orchestration Best Practices: Understand how to effectively manage multi-step workflows and integrate various models to create cohesive AI systems.
Evaluation Techniques: Learn how to implement automated evaluation processes to assess and improve agent performance continuously.
Who should attend
This session is developer-oriented and is a best fit for anyone building gen-AI applications directly. So, full-stack developers, AI engineers, product engineers in similar roles. It’s also a good fit for CTOs and technical leaders who want to understand and improve their team’s AI systems. We will focus on the application side of language models, and won’t be covering training or fine-tuning topics in this track.
