Generative AI apps face risks that classic moderation does not cover: users trying to break the model's rules, malicious instructions hidden in documents, and answers that sound confident but are not supported by the sources. Azure provides several layered guardrails for these, and AI-102 expects you to match each risk to the right control.
Free account
Keep reading for free
Create a free StudyToCert account to read the rest of this lesson: 4 more sections, 4 key terms, a real-world example, an exam tip and self-check questions. Every lesson, lab and practice test is free with an account.