Demo Evenings LDN: Building Agentic Systems with Google AI

Alvaro Silva-Santisteban, AI Solution Lead at Google, shares a practical view of building agentic systems, from choosing the right architecture to implementing trust, governance, and human-in-the-loop safeguards, along with a live demo of Google NotebookLM and Gemini Enterprise.

AI agents are quickly moving from experimentation to real-world deployment, forcing teams to rethink how AI systems are designed, governed, and scaled. Drawing on real examples and live workflows, this session explores how organizations can move beyond demos to deploy agents that deliver reliable, business-ready impact.

Event Overview
As AI agents move into production, teams need systems that can reason, act, and be trusted. In this session, Alvaro Silva-Santisteban shares how agentic systems are designed in practice, from architecture to governance and deployment.

01 - Anatomy of an Agent
A practical breakdown of what actually makes an AI agent work. Alvaro deconstructs the core stack, the Brain (models), Memory (sessions and long-term context), and Hands (function calling and tools), and how these pieces come together to enable reasoning and action.

02 - Choosing the Right Agent Architecture
Not every problem needs the same kind of agent. Learn how to distinguish between retrieval-based agents and action-oriented agents, and how to align each approach to real business needs without over-engineering solutions.

03 - Live Demo
See an agentic workflow come to life using NotebookLM and Gemini Enterprise. Alvaro walks through how teams can structure information, prompt effectively, and guide outputs to support real decision-making, while applying human oversight to keep results accurate and trustworthy.