AI Engineering teams are trying to secure AI systems built from components that didn't exist a year ago: agents, tools, memory, context graphs, orchestration frameworks. Traditional security wasn't built for any of this.
Here are 3 things practitioners are getting wrong right now:
- Agents are the new microservices
- Memory is where sensitive data goes to retire
- Your AI supply chain just got bigger than your software supply chain.
This session covers real architectures, real failure modes, and what runtime data control actually needs to look like when agents are making access decisions you never anticipated.
