Unlocks after Module 8The AI Engineering Program
Module 9: Evals, Guardrails & AI Security
Measure whether an AI system is actually good, catch regressions before users do, and defend it against prompt injection and data leaks.
24guided hours
11lessons
9 of 13in the program
Lessons
11 lessons, in order. Each one unlocks when you finish the one before it.
- 9.1Why AI apps fail silently
- 9.2Error analysis on real traces
- 9.3Golden datasets and synthetic test data
- 9.4Code-based checks and assertions
- 9.5LLM-as-judge, calibrated against human labels
- 9.6Evals in CI: blocking a bad prompt change
- 9.7Tracing and observability with open-source tools
- 9.8OWASP Top 10 for LLM apps: prompt injection, data leakage, excessive agency
- 9.9Guardrails and personal-data redaction
- 9.10Red-teaming your own app
- 9.11Module project
Your first lesson is on us.
AI vs ML vs DL vs GenAI: deep notes, a hands-on lab and a quiz. No card. No catch.