Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
Learn how to securely deploy AI agents in production environments through this 46-minute conference talk from BSidesSF 2025. Explore the inherent risks and challenges of agentic applications, including hallucinations, non-deterministic behavior, vast input spaces, and prompt injection attacks. Discover practical strategies and open-source tools that help mitigate these security threats and reliability issues. Gain insights into best practices for taming the unpredictable nature of AI agents, drawing parallels between the mythical challenge of dragon-taming and the real-world complexities of productionizing agentic systems. Master techniques for building robust defenses against common attack vectors while maintaining the functionality and effectiveness of your AI-powered applications in enterprise environments.
