Pass the Microsoft Certified: Machine Learning Operations (MLOps) Engineer AI-300 Questions and answers with ExamsMirror

Correct sequence:

Create a data asset.

Create a Foundry Search resource.

Create a vector index.

Create a flow.

First, create a data asset so that the locally stored text files are available within the project as a managed data source. The content must then be made searchable for Retrieval-Augmented Generation.

Next, create a Foundry Search resource to provide the search infrastructure that will store and serve the indexed document content. Microsoft documents Azure AI Search as a supported vector store for Foundry and Azure Machine Learning RAG workloads.

Third, create a vector index from the source documents. During vector-index creation, the content is processed into chunks and embeddings, which enables semantic similarity retrieval. Microsoft documents that vector indexes can be created from local files, folders, or registered data assets and then consumed by an Index Lookup operation.

Finally, create a flow and configure it to query the vector index and supply the retrieved context to the connected Azure OpenAI model. Microsoft specifically documents adding an existing vector index to a prompt flow through the Index Lookup tool.

Create a connection is the unused action in this question because the scenario already specifies a connected Azure OpenAI Service model.

Study Guide Reference: Design and implement a GenAIOps infrastructure — RAG architecture, project data, vector indexing, Azure AI Search, prompt flow, and grounding with enterprise content.

The following custom role can do everything in the workspace except for the following actions:

It can ' t create or update a compute resource.

It can ' t delete a compute resource.

It can ' t add, delete, or alter role assignments.

It can ' t delete the workspace.

To create a custom role, first construct a role definition JSON file that specifies the permission and scope for the role. The following example defines a custom role named " Data Scientist Custom " scoped at a specific workspace level:

data_scientist_custom_role.json :

{

" Name " : " Data Scientist Custom " ,

" IsCustom " : true,

" Description " : " Can run experiment but can ' t create or delete compute. " ,

" Actions " : [ " * " ],

" NotActions " : [

" Microsoft.MachineLearningServices/workspaces/*/delete " ,

" Microsoft.MachineLearningServices/workspaces/write " ,

" Microsoft.MachineLearningServices/workspaces/computes/*/write " ,

" Microsoft.MachineLearningServices/workspaces/computes/*/delete " ,

" Microsoft.Authorization/*/write "

],

" AssignableScopes " : [

" /subscriptions/ < subscription_id > /resourceGroups/ < resource_group_name > /providers/Microsoft.MachineLearningServices/workspaces/ < workspace_name > "

]

}

Groundedness and Relevance directly measure the two quality characteristics specified in the requirement.

Groundedness evaluates whether the generated response is supported by the supplied knowledge context rather than introducing unsupported or fabricated information. Microsoft Foundry defines the Groundedness evaluator as measuring how well a generated response aligns with the provided context without fabricating content. For an assistant that relies on internal knowledge sources, this is the primary metric for determining whether its claims are traceable to retrieved evidence.

Relevance evaluates whether the generated response actually addresses the user ' s query. Microsoft defines the Relevance evaluator as measuring how relevant the response is to the query, including whether it appropriately and accurately responds to the user ' s request. This detects responses that may be factually grounded yet tangential or insufficiently focused.

Harmfulness and Fairness are safety-oriented dimensions rather than measures of factual support or query alignment. Tone assesses communication characteristics but does not establish whether a response is supported by source material or relevant to the prompt.

Therefore, the required pair is Groundedness + Relevance .

Study Guide Reference: Implement generative AI quality assurance and observability — Foundry quality evaluators, groundedness, relevance, RAG evaluation, and pre-production validation.

Azure Machine Learning environment versions are effectively immutable with respect to their runtime definition . Microsoft documents that after an environment version has been registered, properties such as the Docker image, build context, and Conda dependencies cannot be modified. Only metadata properties such as the description and tags can be updated. Therefore, when a newer Docker image must be used, the correct approach is to define an Environment object representing a new environment version and register it with Azure Machine Learning.

For example, the new environment version can retain the existing environment name while specifying the updated image URI/tag and a new version. Registering an environment with the same name creates another version, preserving reproducibility for jobs that depend on the previous version.

Option A changes only descriptive metadata and has no effect on the execution image. Option B is incorrect because conda_file defines Python/Conda package dependencies rather than the Docker image version. Option C incorrectly implies that an existing registered environment ' s image tag can be modified through create_or_update; Microsoft explicitly states that the image is immutable after registration.

Study Guide Reference: Implement machine learning model lifecycle and operations — Azure Machine Learning environments, versioned assets, reproducible training environments, and SDK v2 asset management.