AB-100: Agentic AI Business Solutions Architect › Practice Assessment for Exam AB-100: Agentic AI Business Solutions Architect › Question #26610
Single Choice Moderate

Q

A company deploys an enterprise assistant that uses Azure OpenAI in a production subscription.

Different teams at the company deploy different model names and versions, making it difficult to audit and standardize production deployments.

You need to implement an ALM control that prevents deploying any model that is NOT on an approved allowlist, which the teams can update through a controlled process.

What should you do in the production subscription?

ID: #26610 Practice Assessment for Exam AB-100: Agentic AI Business Solutions Architect 4 views
Question Info
#26610Q ID
ModerateDifficulty
Practice Assessment for Exam AB-100: Agentic AI Business Solutions ArchitectTopic
Start Quiz on This Topic
 Your Answer

Choose the Best Option

Click any option to instantly check if you're correct.

  • A Maintain an approved model allowlist and monitor deployments for noncompliance. ✔ ✖
  • B Enforce an approved model allowlist by using deployment pipeline approval gates. ✔ ✖
  • C Require the teams to select models from only an approved allowlist documented in internal standards. ✔ ✖
  • D Create a custom Azure policy that blocks Azure OpenAI model deployments unless the model name is on an approved allowlist. ✔ ✖
Correct Answer

Explanation

Objective:

3.3 Design the ALM process for AI-powered business solutions

What This Item Tests:

Design the ALM process for custom AI models

Additional Reading:

Best practices

What is Azure Policy?

Rationale:

A custom Azure policy enforces a preventive, subscription-level ALM control by blocking unapproved model deployments before they reach production, while still allowing controlled updates to the allowlist. Pipeline gates, post-deployment monitoring, and documented standards rely on process or detection and do not provide enforceable platform-level prevention.

 Continue Practice
Previous Question Next Question
 Share

Share This Question

Challenge a friend or share with your study group.

 More from This Topic

Related MCQ Questions

A company has two production agents: One is built in Microsoft Copilot Studio, and the other is built in Microsoft Foundry. Both agents send telemetry to the same Azure Monitor Application Insights resource. U... A company has a multi-agent solution built in Microsoft Foundry. The solution grounds responses in internal HR documents and uses agent tools to call internal and external systems. Security testing shows that ... A company uses an agent built in Microsoft Foundry that retrieves internal content and invokes tools to perform actions. Security testing shows that prompt injection attacks can trigger unauthorized tool calls... A company has a Microsoft Copilot Studio agent grounded in a Microsoft SharePoint Online knowledge source. After adding new knowledge documents and updating the agent instructions, responses to the same user q... A company has a customer service agent built in Microsoft Foundry that calls an Azure OpenAI model and a knowledge API. Telemetry and online evaluation scores are sent to Azure Monitor Application Insights. Us... A company has a Microsoft Copilot Studio agent that performs browser-based automation against a legacy web app by using the Computer Use tool. When multiple users trigger the automation simultaneously, some ru... A company uses Microsoft Dynamics 365 Sales with a custom model-driven app that sellers use instead of the standard Sales Hub app. The sellers cannot open the Copilot immersive experience from the custom app n... A company uses Microsoft Dynamics 365 Supply Chain Management with customizations developed in Microsoft Visual Studio and stored in Azure Repos. Deployable packages are published to the Lifecycle Services (LCS... A company uses a Microsoft Copilot Studio agent across multiple Dynamics 365 apps to generate natural language responses. The agent supports English and Spanish and relies on Dynamics 365 data and business logi... A company has a Microsoft Copilot Studio agent that uses an AI approval stage to approve or reject employee expense reimbursement requests. Identical requests sometimes produce different decisions, and the log...