Track 15: Frontier and Advanced
AI Security: Prompt Injection, OWASP LLM Top 10 & Guardrails
15 lessons
Track 6: AI Agents, Human-in-the-Loop and Guardrails
Guardrails: Inputs, Outputs, Sandboxes, Least Privilege
Block unsafe inputs/outputs and sandbox agent actions.
Part of Build AI Agents and Apps (75 of 88)
Get notified on YouTube Udemy certificate: coming soon
Course
AI Security: Prompt Injection, OWASP LLM Top 10 & Guardrails
Udemy: coming soon
Tools
- Guardrails AI (open-source, freemium)
- NeMo Guardrails (open-source, free)
- OpenAI Agents SDK (open-source)
Watch first
Then try
In this module
- Human-in-the-Loop Explained
- Guardrails: Inputs, Outputs, Sandboxes, Least Privilege
- Evaluate Agents: Trajectories and Tool Use
The course this lesson belongs to