AI-300 Exam Question 11
A team develops and manages a conversational assistant by using Microsoft Foundry.
The team must be able to validate that the assistant does not produce hateful responses before the application is exposed to any users.
You need to evaluate the model output for hateful responses as part of a repeatable validation process.
Which evaluator should you configure first?
The team must be able to validate that the assistant does not produce hateful responses before the application is exposed to any users.
You need to evaluate the model output for hateful responses as part of a repeatable validation process.
Which evaluator should you configure first?
AI-300 Exam Question 12
A team is experimenting with traditional models for a classification workflow in Azure Machine Learning.
The team requires a consistent way to manage assets that are created during experimentation.
You need to ensure that artifacts can be reused and governed across projects.
Which asset should you register?
The team requires a consistent way to manage assets that are created during experimentation.
You need to ensure that artifacts can be reused and governed across projects.
Which asset should you register?
AI-300 Exam Question 13
Hotspot Question
You manage a Retrieval-Augmented Generation (RAG) system that retrieves internal policy documents from a vector index.
Recent analysis shows that:
- Retrieved results frequently include duplicated content from the same document.
- Retrieved chunks sometimes span unrelated policy sections.
You review the following retrieval and ingestion configurations:
You need to reduce duplicated retrieval results and improve chunk relevance across policy sections. For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
You manage a Retrieval-Augmented Generation (RAG) system that retrieves internal policy documents from a vector index.
Recent analysis shows that:
- Retrieved results frequently include duplicated content from the same document.
- Retrieved chunks sometimes span unrelated policy sections.
You review the following retrieval and ingestion configurations:
You need to reduce duplicated retrieval results and improve chunk relevance across policy sections. For each of the following statements, select Yes if the statement is true. Otherwise, select No.
NOTE: Each correct selection is worth one point.
AI-300 Exam Question 14
A team manages an Azure Machine Learning workspace where they deploy models to online endpoints.
The team needs to introduce a new version of a model to production without disrupting existing users.
The team must validate the new version before full rollout.
You need to reduce risk during deployment.
What should you do?
The team needs to introduce a new version of a model to production without disrupting existing users.
The team must validate the new version before full rollout.
You need to reduce risk during deployment.
What should you do?
AI-300 Exam Question 15
You deploy a new model version to a managed online endpoint. You must test it with 10% traffic and automatically roll back if latency or error rate increases beyond threshold. What should you configure?