AI-103: Developing AI Apps and Agents on Azure

By Microsoft · Question Mode

QuestionQ145

VerifiedImplement generative AI and agentic solutions

You have an Azure subscription containing a Microsoft Foundry resource named AI1 and a Content Safety in Foundry Control Plane resource named CS1.

You build an agent that uses AI1 to generate answers to specific questions and uses CS1 to check both input and output for objectionable content.

You need to optimize the content filter configurations by testing sample questions.

Solution: In Content Safety Studio, you use the Safety metaprompt feature to perform the tests.

Does this satisfy the requirement?

Explanation

Safety metaprompts guide a model’s behavior as a complementary safety layer; they are not a mechanism for testing or optimizing content-filter configurations. Content Safety’s text-moderation testing experience evaluates sample text against configured severity thresholds and returns moderation results, which supports filter tuning.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!