Enterprise AI in Production

{Describe your session in 2 paragraphs}
Modern AI systems increasingly rely on agents and automated workflows that interact with databases, APIs, and external services. While databases like PostgreSQL provide strong controls for who can access data, they do not govern how that data us used once retrieved.
In practice, agent-driven pipelines can query sensitive data and then propagate it across systems, often without visibility, control, or enforcement. This creates a critical gap where seemingly valid operations can lead to unintended data exposure.
This lightning talk demonstrates a production-style agent workflow where an LLM-powered agent retrieves data and decides how to act on it. Through a live, minimal system, we show how data can be exfiltrated via agent actions and how introducing a platform-level governance layer enforces policy controls on outbound data usage. The session focuses on execution traces, failure handling, and how centralized enforcement provides safety without modifying application logic.

{Mention 1-2 takeaways from your session}

1. Why controlling data access is not enough in AI systems, you must control data usage and movement
2. How to introduce policy-based enforcement for agent actions to prevent unintended data exfiltration

{Which audiences is your session going to beneficial for?}
Backend engineers working with data pipelines and APIs, Engineers interested in governance, security, and observability in AI systems.

{Add your bio - who you are; where you work}
Kanika Singhal is a technical leader in Flow Network Security at Nutanix with over 15 years of experience in networking and security. Prior to Nutanix, she worked on SD‑WAN technologies at VMware.
LinkedIn - https://www.linkedin.com/in/kanika-singhal-8bb3622b/