Microsoft AB-100 Online Practice Questions and Exam Preparation

Microsoft AB-100 Online Questions & Answers

• Question 131:

  A company uses a fine-tuned Microsoft Foundry model that requires frequent updates as new customer feedback becomes available.

  You need to design an application lifecycle management (ALM) process that meets the following requirements:

  1. Data changes must be tracked and versioned.

  2. The model must be retrained consistently by using approved training data.

  Which two actions should you include in the design? Each correct answer presents part of the solution.

  NOTE: Each correct selection is worth one point.

  A. Associate the storage location to the fine-tuning job.
  B. Create a content filter.
  C. Store the training data in Azure Files.
  D. Upload the training data to Microsoft Foundry data files
  E. Store the training data in Azure Blob Storage that has version control enabled.
  D. Upload the training data to Microsoft Foundry data files
  E. Store the training data in Azure Blob Storage that has version control enabled.

  ---

  Explanation

  Uploading training data to Microsoft Foundry data files and storing the source data in version-enabled Azure Blob Storage supports consistent retraining from approved data. Blob versioning tracks changes to the training set, while Foundry data files make the approved dataset available to the fine-tuning job. Content filters do not version data, and unversioned file storage would not meet the audit requirement. Frequent model updates require governed data versioning.

• Question 132:

  A department wants to customize Microsoft 365 Copilot for a contract-review process. Users should stay in the Microsoft 365 Copilot experience, and the solution should use instructions, knowledge, and actions scoped to the contract-review scenario.

  What should you build?

  A. A standalone website with a search box
  B. A declarative agent for Microsoft 365 Copilot
  C. A Power BI dashboard with natural language Q&A
  D. A manually curated email template library
  B. A declarative agent for Microsoft 365 Copilot

  ---

  Explanation

  A declarative agent for Microsoft 365 Copilot is the right fit because users should stay in the Microsoft 365 Copilot experience while the agent adds instructions, knowledge, and actions for a specific process. It customizes Copilot behavior without requiring a standalone app. Copilot Studio and Foundry are useful for other agent patterns, but the requirement is an extension inside Microsoft 365 Copilot. Use declarative agents when the workflow lives in the Microsoft 365 Copilot shell.

• Question 133:

  HOTSPOT

  You are designing a testing solution for Microsoft Copilot Studio agents.

  You need to validate prompt engineering best practices to ensure that the agents generate accurate and contextually relevant responses.

  Which prompt validation techniques and metrics should you include in the solution? To answer, select the appropriate options in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  The completed hotspot uses varied prompt phrasing as the validation technique and response relevance and accuracy as the metric. The answer image tests whether the agent performs well across realistic wording rather than only one simple prompt. Relevance and accuracy measure whether the generated response addresses the user need correctly. Excluding domain terminology or counting generated words would not validate business usefulness.

• Question 134:

  A company plans to deploy a Microsoft Copilot Studio agent to enhance customer support.

  The company stores customer data across ServiceNow, Microsoft Dynamics 365 Finance, Dynamics 365 Supply Chain Management, and Excel files in SharePoint Online.

  You need to recommend a solution to ensure that the agent can deliver accurate and timely responses.

  What should you recommend?

  A. Implement a model router for query handling.
  B. Create custom prompts.
  C. Implement Microsoft Power Platform connectors.
  D. Enable incremental indexing in Azure AI Search.
  D. Enable incremental indexing in Azure AI Search.

  ---

  Explanation

  Incremental indexing in Azure AI Search is appropriate when data comes from multiple enterprise systems and must stay current without rebuilding the whole index. It improves freshness and efficiency by updating only changed content. This is more suitable than manually reloading all sources or relying on the agent to discover changes at runtime. Use incremental indexing when the scenario emphasizes many systems, changing data, and searchable grounding content.

• Question 135:

  A company has a canvas app named App1 in a Microsoft Power Platform environment named Env1.

  Env1 uses a customer-managed key for data encryption. App1 connects to multiple data sources to retrieve and update customer and order information.

  You need to recommend a solution to add Microsoft Copilot components to App1. The solution must NOT modify the current security or encryption configurations of Env1.

  What should you include in the recommendation?

  A. Modify the data sources of App1 to make them compatible with Copilot.
  B. Duplicate App1 and republish the app in Env1.
  C. Enable Copilot features for Env1.
  D. Move App1 to a new environment that uses Microsoft-managed keys.
  D. Move App1 to a new environment that uses Microsoft-managed keys.

  ---

  Explanation

  Moving the canvas app to an environment that uses Microsoft-managed keys is necessary because the current environment uses a customer-managed key and the requirement depends on Microsoft-managed encryption. Encryption behavior is an environment-level platform setting, not something fixed by editing a connector or app formula. A new environment with the required key management model gives the app the needed data protection baseline. For Power Platform encryption requirements, check the environment configuration first.Question Set 1

• Question 136:

  A company has a Microsoft Power Platform environment that contains Microsoft Dataverse data.

  You create a Microsoft Copilot Studio agent named Agent1 that processes the Dataverse data.

  You discover that Agent1 fails to return relevant or accurate results.

  You need to improve the quality and reliability of data grounding.

  What should you do?

  A. Retrain Agent1.
  B. Verify and cleanse the Dataverse data.
  C. Use an adaptive card in Agent1.
  D. Add example user inputs to the training data of Agent1.
  B. Verify and cleanse the Dataverse data.

  ---

  Explanation

  Verifying and cleansing Dataverse data is the first fix because the agent processes Dataverse records and the issue is caused by the quality of the source data. AI grounded in inaccurate, stale, or duplicate business data will produce unreliable results even if the model and prompts are sound. Changing the agent alone would not remove bad source records. Always improve grounding data quality before tuning prompts or orchestration for data-driven inaccuracies.