The Complete AI Security Course In 8 Hours - AI Guardrails, LLM Evals & Memory And AgentOps
Krish Naik
Four modules on running LLM applications in production, each taught by a different instructor. The first sets up guardrails against prompt injection and jailbreaks with NeMo Guardrails, the second evaluates a RAG system with Ragas metrics, and the third goes through more than a dozen memory techniques for agents. The last module builds an agentic RAG app, traces it with Langfuse and deploys it on Amazon EKS.
What you'll learn
- Blocking prompt injection and jailbreaks with NeMo Guardrails
- Evaluating RAG with Ragas metrics and golden datasets
- Short-term, long-term, episodic and semantic memory for agents
- Tracing agents with Langfuse and Pydantic Logfire
- Deploying and autoscaling an agent on Amazon EKS
