Your Model is Private. Your System Isn't.

Official Schedule Context

Privacy in AI isn't just about choosing the right model. Data leaks rarely happen inside the LLM

itself - they happen in the systems surrounding it. Observability pipelines, analytics platforms,

prompts, agents, and infrastructure often become accidental channels for exposing user data. In this

session, Joshua Mo, Lead DevRel Engineer at Venice AI, explores why private models alone are not

enough and shares practical privacy-preserving patterns that AI engineers can adopt today. From

revocable handles and hashed identifiers to agent boundaries and confidential computing, attendees

will leave with concrete ideas for building AI systems that protect user data by design.

No official session recording transcript was found by exact title match on the AI Engineer YouTube channel during this run.

Pending transcript synthesis when an official recording or confirmed matching video is available.