AI-300: Operationalizing Machine Learning and Generative AI SolutionsDemo

By Microsoft · Question Mode

QuestionQ15

Implement generative AI quality assurance and observability

A team is using Microsoft Foundry in a development environment to test and compare large language model (LLM) prompt variants.

The team needs consistent inputs to assess prompt variants without depending on live user traffic.

You need to create a controlled input-data evaluation. Which action should you take first?

  • A Generate synthetic interaction data.
  • B Configure content filters.
  • C Apply a blocklist.
  • D Enable observability metrics.
Explanation

Synthetic interaction data supplies a controlled, repeatable evaluation dataset when live production traffic is unavailable. Microsoft Foundry can generate synthetic test queries and store them as a reusable dataset, enabling consistent comparison of prompt variants. Content filters, blocklists, and observability metrics do not create the required input data.

Learn more

Community Discussion

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