How do LLM agents turn plain English into complex action? This talk demystifies their inner loop, tool calls, memory, error handling, and goal pursuit, through a from fundamental deep dive into the mechanics that make real-world agents work. We'll start off which classical RL based agents and use that framework to understand cutting edge current LLM powered agents.

Learn the architecture of LLM Agents and their applications in task automation, focusing on code generation and the use of external APIs and tools.

Tackle the common challenges encountered during the development of LLM Agents, and see how integrations with Weights & Biases can provide clarity and control through 'Traces' and 'Prompts'.

Discuss various strategies for evaluating and testing LLM Agents, including A/B testing and performance metrics.

Experience a hands-on segment where you'll work on setting up a minimal LLM Agent, addressing real-world automation tasks, and understanding the step-by-step process of agent development and deployment.

Foundations of LLMs and Python Basics; Understanding Natural Language Processing; Transformers and Attention; LLM Development: Fine-tuning and Prompt Engineering; Retrieval-Augmented Generation (RAG); Introduction to LLM Agents; Advanced Topics for Production LLM Application