Ai+ Training

Agents are all the rage in 2026: they are the way to go beyond basic LLM question-and-answer patterns into an entirely new programming paradigm in which software is given an objective and a set of tools and figures out on its own how to achieve that goal. Agents can not only produce dramatically better, more accurate results in response to queries, but they can be integrated directly into software to accept structured input and take action """"under the hood"""", without needing a """"chat"""" interface at all.

LlamaIndex is at the forefront of building real-world agentic applications, and in this session we'll show you how that's done. We'll start by running you through the most common design patterns for agentic applications including chaining, routing, parallelization, orchestrator-workers and evaluator-optimizers. We'll show you how these patterns can be implemented in LlamaIndex.