Extracurricular Tech Talks - AI Guardrails

​What you will learn:

• ​What AI guardrails are and why they matter

• ​Common risks in modern AI systems, including hallucinations and unsafe outputs

• ​Human-in-the-loop approaches and oversight mechanisms

• ​LLM-in-the-loop approaches

• ​Technical guardrails: validation, filtering, monitoring, and policy enforcement

• ​Safety challenges in agentic AI and tool-using systems

• ​Best practices for deploying trustworthy AI applications

​Open to all current & former BAU students.