Q31. Hotspot Question
You manage a Retrieval-Augmented Generation (RAG) system that uses Azure AI Search to retrieve documents from an indexed knowledge base.
The system must support the following retrieval requirements:
– Queries that include exact policy identifiers must return matching
documents even when semantic similarity is low.
– Natural-language questions must prioritize semantically relevant
documents even when keywords are not an exact match.
You need to configure the retrieval approach to meet the requirements.
How should you configure the retrieval behavior for each requirement? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.

Q32. A team plans to deploy a large foundation model in Microsoft Foundry as part of a new enterprise AI capability.
Different business units across the team’s organization will access the model from various internal applications.
You need to deploy a foundation model by minimizing latency.
Which deployment type should you use?

Q33. Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear on the review screen.
You work in Microsoft Foundry with a prompt flow.
You must manually evaluate prompts and compare results across prompt variants.
You need to capture the inputs, outputs, token usage, and latencies for each flow run for the evaluation.
Solution: In Microsoft Foundry, turn on Tracing for the prompt flow of the project and execute test runs to produce trace data.
Does the solution meet the goal?

Q34. A team manages an Azure Machine Learning workspace and deploys a model to an endpoint.
A deployed online endpoint shows inconsistent response times during periods of high traffic.
You need to identify potential performance degradation.
Which three metrics should you monitor? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point. Choose three

Q35. Drag and Drop Question
A company plans to deploy a foundation model in Microsoft Foundry.
The mode must support the following workloads:
– A customer support workload used across multiple regions
– A marketing workload that must remain within a specific region due to data residency requirements You need to select the deployment type.
Which deployment type should you use for each workload? To answer, move the appropriate deployment types to the correct requirements. You may use each deployment type once, more than once, or not at all. You may need to move the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.

Q36. Drag and Drop Question
You develop a flow for a Microsoft Foundry project.
You plan to use outputs generated by running the flow to determine the following information:
– the number of tokens used by each large language model (LLM) node of
the flow
– the accuracy of the model used by the flow
You need to examine the output that provides the required information.
Which output type should you examine? To answer, move the appropriate output types to the correct evaluations. You may use each output type once, more than once, or not at all. You may need to move the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.

Q37. A team runs training and inference jobs in Azure Machine Learning.
The team experiences inconsistent runtime dependencies that cause variation in results.
You need to ensure that all jobs use the same execution dependencies.
Which asset should you define?

Q38. Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear on the review screen.
You manage an Azure Machine Learning workspace. The Python script named script.py reads an argument named training_data.
The training_data argument specifies the path to the training data in a file named dataset 1. csv.
You plan to run the script.py Python script as a command job that trains a machine learning model.
You need to provide the command to pass the path for the dataset as a parameter value when you submit the script as a training job.
Solution: python script.py –trainingdata ${{inputs.training_data}}
Does the solution meet the goal?

Q39. Hotspot Question
A team manages an Azure Machine Learning workspace to train and register machine learning models.
Previous model versions must be retained for audit and rollback purposes but must not be used for new deployments.
You need to manage model versions.
What should you do for each requirement? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.

Q40. A company has multiple data science teams working on separate machine learning projects.
The company requires models to be auditable, reusable, and governed centrally across teams.
The models must allow team-level isolation for billing.
You need to establish the foundation for governed machine learning operations.
Which action should you perform first?

Q41. You need to standardize how Fabrikam Inc. manages machine learning assets.
Which action should you perform first?

Q42. You manage an Azure Machine learning workspace. You develop a machine learning model.
You must deploy the model to use a low-priority VM with a pricing discount.
You need to deploy the model.
Which compute target should you use?

Q43. Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.
You work in Microsoft Foundry with a prompt flow.
You must manually evaluate prompts and compare results across prompt variants.
You need to capture the inputs, outputs, token usage, and latencies for each flow run for the evaluation.
Solution: Configure Azure Monitor to collect logs from the workspace. Use the logs to perform prompt evaluation.
Does the solution meet the goal?

Q44. 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?

Q45. Drag and Drop Question
You use Azure Machine Learning to deploy a model as a real-time web service.
You need to create an entry script for the service that ensures that the model is loaded when the service starts and is used to score new data as it is received.
Which functions should you include in the script? To answer, drag the appropriate functions to the correct actions. Each function may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.

Q46. A team deploys a machine learning model to a managed online endpoint. The team monitors model performance and data quality metrics in production.
When monitoring thresholds are exceeded, the team requires an automated operational response that notifies downstream systems.
You need to configure the monitoring solution to meet the requirements.
Which configuration should you associate with each requirement as a first step? To answer, move the appropriate configurations to the correct requirements. You may use each configuration once, more than once, or not at all. You may need to move the split bar between panes or scroll to view content . NOTE: Each correct selection is worth one point.

Q47. Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.
After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear on the review screen.
You work in Microsoft Foundry with a prompt flow.
You must manually evaluate prompts and compare results across prompt variants.
You need to capture the inputs, outputs, token usage, and latencies for each flow run for the evaluation.
Solution: Use the prompt flow SDK to enable tracing for the flow before executing runs. Then run the flow to generate traceable results.
Does the solution meet the goal?

Q48. A team develops and manages a conversational assistant by using Microsoft Foundry.
The team requires generative AI to automatically evaluate every pull request of an agentic application and fail the build if safety thresholds are exceeded.
You need to automate evaluations as part of CI.
What should you configure?

Q49. Case Study 1 – Fabrikam Inc.
Background
Fabrikam Inc. is a mid-sized healthcare analytics company that provides population health dashboards and predictive insights to regional hospital systems across the United States.
Fabrikam Inc. customers rely on near real time analytics to monitor patient flow, staffing needs, and readmission risks. They use multiple traditional forecasting machine learning models for predictions.
Fabrikam Inc. has an established Microsoft Azure footprint. The company uses Jupyter Notebooks that run on a local server as the primary development environment. The data science team is experiencing scalability, asset management and code management issues with the current development platform. Fabrikam Inc. plans to migrate to a cloud-based development environment to mitigate the issues.
Additionally, the company plans to implement a Retrieval-Augmented Generation (RAG)-based chat application for client support. Leadership requires the application to be developed and deployed with a low operational risk.
Current Environment
Fabrikam Inc. operates a single Azure subscription that has the following components:
* Azure Data Lake Storage Gen2 that contains de-identified clinical and operational datasets
* Azure AI Search indexing curated analytical documents and reference materials
* A small set of Python-based training scripts maintained by data scientists
* Azure OpenAI Service with deployed foundational models
* A Microsoft Foundry resource for building a RAG-based solution
Evaluation data has manually defined expected responses.
The current challenges faced by the data science team include the following:
* Model training jobs are run manually from notebooks.
* Experiment tracking is inconsistent
* Model versions are registered without standardized metadata.
* Deployment is performed manually by data scientists, with limited rollback capability.
* The team has no standardized evaluation process for generative AI outputs.
The environment currently allows public network access. Authentication relies on user accounts rather than managed identities. Compute targets are manually created and shared across experiments. This has led to resource contention during peak usage.
Business Requirements
Fabrikam Inc. has the following business requirements for the modernization initiative:
* Provide a conversational interface that answers analytics questions by using internal documents and datasets.
* Ensure that sensitive healthcare-related data is not exposed outside the Fabrikam Inc. Azure tenant.
* Enable repeatable and auditable model training and deployment processes.
* Support experimentation to compare prompt strategies and fine-tuned models.
* Align the model with the ranked preferences and optimize behavior for the long term.
* Minimize disruption to existing analytics workloads during rollout.
Technical Requirements
To support the business goals, Fabrikam Inc. identifies these technical requirements:
* Use Azure Machine Learning workspaces to centrally manage data assets, models, and environments.
* Implement experiment tracking and model versioning for all training jobs.
* Orchestrate training and evaluation by using pipelines rather than manually running notebooks.
* Deploy traditional machine learning models with support for staged rollout and rollback.
* Improve RAG-based solution output quality.
* Use the existing evaluation datasets that are based on real data with input-output pairs.
* Apply advanced fine-tuning techniques only when prompt engineering is insufficient Issues and Constraints Fabrikam Inc. must comply with internal security policies that require the company to restrict network access and avoid long-lived secrets. The data science team has limited Azure DevOps experience, so solutions must favor managed services and automation over custom infrastructure.
Cost predictability is important. Leadership prefers serverless or managed compute options where possible but is willing to approve dedicated compute for stable production workloads.
Problem Statement
Fabrikam Inc. must design and implement an Azure-based AI operations solution that enables reliable training, evaluation, deployment, and iteration of generative AI models. The solution must support experimentation and gradual rollout while ensuring governance, security, and operational stability. The data science and platform teams must collaborate to deliver this solution by using Azure Machine Learning and Microsoft Foundry capabilities.
You need to improve a GPT-5 model performance based on Fabrikam Inc.’s technical requirements. Which action should you perform first?

Q50. A team schedules weekly retraining of a model using Azure ML pipelines. They also want retraining triggered automatically when production data significantly deviates from training data distribution, without duplicating pipeline logic. What should they implement?