Beginner Italian 45 min

Agentic Hardening: Enterprise-Grade Safety on LLMs with Google Cloud Model Armor

Tema: AI e ML, Cloud Orario: 17 ott, 15:45 Aula: A3

Abstract

In the era of autonomous agents, a standard safety filter is no longer enough. When we give agents the power to reason, access data, and execute tools, we open a massive new attack surface. How do we prevent prompt injections, PII leakage, and jailbreaks in a multi-agent system?

In this session, we will explore how to secure agentic workflows using Google Cloud Model Armor. We will explore Intent-based Protection, Data Sanitization & Redaction, Governance at Scale.

It’s time to move from experimental AI to production-ready systems. Let’s see how to shield your models and protect your users without killing the 'magic' of the agent.

Speaker

Gregorio Palamà

Gregorio Palamà

GDE Cloud | Senior Enterprise Architect @ adesso.it | Community Manager @ GDG Pescara

I have been working in the IT industry for over 15 years. I currently hold the role of Senior Enterprise Architect in adesso.it. I am a Google Developer Expert on GCP and a Google Cloud Innovator Champion on the topic of modern architecture. I manage GDG Pescara together with other developers, I love sharing my knowledge and trying to do it in a fun way.