Talk Outline

Deep dive into the foundations of Generative AI, covering the history of Natural Language Processing (NLP) leading up to Large Language Models (LLMs) and their limitations, particularly the grounding problem. It then focuses on modern methods to enhance LLM capabilities, specifically Function Calling and Retrieval Augmented Generation (RAG), before introducing the Agent Development Kit (ADK) as a flexible framework for developing and deploying multi-agent systems, complete with concepts for tools, conversational context, and evaluation.

<aside> <img src="notion://custom_emoji/9067698e-8c48-4c31-9814-0f22ae0539d7/378c01c2-41b2-802a-941e-007a5d32fd71" alt="notion://custom_emoji/9067698e-8c48-4c31-9814-0f22ae0539d7/378c01c2-41b2-802a-941e-007a5d32fd71" width="40px" />

Tool Focus: Google Cloud Platform (GCP)

</aside>

Speaker Bio

Felipe Catalano is a Customer Engineer at Google Cloud in London, where he works closely with early-stage startups across the UK and Ireland. Originally from Brazil, Felipe has spent over a decade deeply involved in traditional infrastructure. He joined Google over four years ago and now specializes in helping founders and engineering teams build strong foundations and scale their businesses using the Google Cloud Stack