Enterprise AI Showcase - Agents Security
About the event
** Pre-register on the [AICamp event website](https://www.aicamp.ai/event/eventdetails/W2026101622) is required for admission.
Description: Welcome to the Enterprise AI Showcase in Bangalore, in collaboration with Snowflake, ANSR. Join us for deep dive tech talks on AI, GenAI, LLMs and machine learning, networking with speakers and fellow developers. Agenda: • 10:00am\~10:30am: Checkin • 10:30am\~10:45am: Welcome and Intro • 10:45am\~12:00pm: Tech talks and Q&A • 12:00pm\~1:00pm: Networking and Snacks
Tech Talk 1: Your Cortex Agent Passed Every Eval. It's Still Not Safe Speaker: Sandip Pani (Snowflake) Abstract: Agent evals measure whether your AI gets the right answer, not what happens when it's attacked. As agents gain tool access and data permissions, prompt injection and jailbreak attempts become a real production risk. This talk breaks down the emerging attack surface of AI agents and how Snowflake is building security into the data and control plane itself. We'll cover Cortex AI Guardrails for real-time prompt injection and jailbreak defense, data-layer protection via RBAC and Row Access Policies, account-level guardrail configuration for "define once, enforce everywhere" governance, and the newly announced Cortex AI Gateway and Agent Identity, Which govern what agents can actually do, and who's accountable when something goes wrong.
Speakers/Topics: Stay tuned as we are updating speakers and schedules. If you have a keen interest in speaking to our community, we invite you to submit topics for consideration: [Submit Topics](https://forms.gle/JkMt91CZRtoJBSFUA)
Sponsors: We are actively seeking sponsors to support AI developers community. Whether it is by offering venue spaces, providing food, or cash sponsorship. Sponsors will not only speak at the meetups, receive prominent recognition, but also gain exposure to our extensive membership base of 30,000+ AI developers in Bangalore and 500K+ worldwide.
