AI in practice: Guardrails and security for LLMs

About this episode

The episode discusses practical guardrails for LLMs with a focus on preventing PII leaks and evaluating safety.

In this episode, we talk about practical guardrails for LLMs with data scientist Nicholas Brathwaite. We focus on how to stop PII leaks, retrieve data, and evaluate safety with real limits. We weigh managed solutions like AWS Bedrock against open-source approaches and discuss when to skip LLMs altogether. • Why guardrails matter for PII, secrets, and access control • Where to place controls across prompt, training, and output • Prompt injection, jailbreaks, and adversarial handling • RAG des...

People in this episode

Hosts: Dr. Andrew Clark, Dr. Sid Mangalik

Guest: Nicholas Brathwaite

Topics covered

• guardrails
• LLMs
• PII leaks
• data retrieval
• safety evaluation
• managed solutions
• open-source approaches

Keywords

• guardrails
• LLMs
• PII
• data security
• prompt injection
• adversarial handling
• AWS Bedrock
• open-source

Mentioned in this episode

Organizations: AWS Bedrock

More episodes of The AI Fundamentalists

• Metaphysics and modern AI: What is Reasoning and Thinking? · May 5, 2026 · 30 min
• Beyond Boosted Trees: Christoph Molnar on the Rise of Tabular Foundation Models · April 21, 2026 · 32 min
• AI and the lost art of reading · March 3, 2026 · 46 min
• Metaphysics and modern AI: What is causality? · January 27, 2026 · 36 min
• Why validity beats scale when building multi‑step AI systems · January 6, 2026 · 40 min
• 2025 AI review: Why LLMs stalled and the outlook for 2026 · December 22, 2025 · 42 min