Building AI-powered applications requires more than connecting a language model to an interface. This session introduces the foundational concepts behind modern AI apps, including prompt structure, context management, and system orchestration.

A central focus of the talk is agent-based architectures: how agents are constructed from models, tools, memory, and control loops, and which patterns are commonly used in practice. We’ll also cover evaluation strategies for probabilistic systems, showing how to measure task success, faithfulness, cost, and reliability. Finally, the session highlights common challenges with agent systems—such as loss of control, debugging difficulty, and cost explosion—and how to design around them.

Attendees will leave with a clear mental model and practical guidance for building AI-powered applications that are evaluable, observable, and ready for real-world use.