Free Microsoft AI-102 Practice Exam with Questions & Answers | Set: 4

To prevent an Azure OpenAI model (such as GPT-4 or GPT-3.5) from returning outputs that include hate speech, you must configure Azure AI Content Safety content filters on the model deployment. Content filters evaluate prompts and/or completions for categories like Hate/Unfairness, Harassment/Violence, Sexual, and Self-harm and can block or redact responses when they exceed your selected threshold. Applying a content filter to Model1 ensures that App1 will not return hate speech, satisfying the requirement.

Why the other options are incorrect:

A. Frequency penalty – discourages token/repetition in output; it does not moderate harmful content.

B. Abuse monitoring – provides telemetry/policy monitoring for potential misuse; it is not a response-time content filter and does not block specific hate content.

D. Temperature – adjusts randomness/creativity; it does not enforce safety.

Microsoft Azure AI References

Azure OpenAI Service – Safety system & content filtering (configure per deployment; categories include Hate).

Azure AI Content Safety – Overview and moderation categories.

Azure OpenAI Studio – Attach Content Safety filters to deployments (prompt/completion filtering).

Comprehensive Detailed Explanation

Looking at the exhibit:

The GetWeather dialog is set up with a trigger phrase:

“what is the weather like in {city=Seattle}”

Here, city is an entity (ex: Seattle, New York, London, etc.).

1. User asks “what is the weather like in New York”

Since “New York” matches the city entity, the bot will correctly identify New York as a city entity.

It will not confuse it with a state entity, nor default to Seattle, because entity recognition extracts the correct city name dynamically.

Correct choice: Identify New York as a city entity

2. GetWeather dialog trigger

In Bot Framework Composer, the trigger type determines how the dialog is activated.

Since GetWeather is linked to the intent “GetWeather” from the Language Understanding model (LUIS/CLU), the trigger is Language Understanding Intent recognized.

This means whenever the user utterance maps to the GetWeather intent, the dialog starts.

Correct choice: Language Understanding Intent recognized

Correct Answer:

Identify New York as a city entity

Language Understanding Intent recognized

Microsoft References

Bot Framework Composer – Triggers

Entities in Conversational Language Understanding

Video Indexer supports multiple Person models per account. Once a model is created, you can use it by providing the model ID of a specific Person model when uploading/indexing or reindexing a video. Training a new face for a video updates the specific custom model that the video was associated with.

Note: Video Indexer supports face detection and celebrity recognition for video content. The celebrity recognition feature covers about one million faces based on commonly requested data source such as IMDB, Wikipedia, and top LinkedIn influencers. Faces that aren ' t recognized by the celebrity recognition feature are detected but left unnamed. Once you label a face with a name, the face and name get added to your account ' s Person model. Video Indexer will then recognize this face in your future videos and past videos.

Comprehensive Detailed Explanation

The method shown uses the Read API of the Azure Computer Vision client library. The ReadAsync call submits the OCR job and returns an Operation-Location header, which contains the operationId. Then GetReadResultAsync(Guid.Parse(operationId)) is called to fetch the result.

The Issue

The Read API is asynchronous.

Submitting the read request does not mean the OCR has finished.

If you immediately call GetReadResultAsync , the operation may still be in progress, resulting in incomplete or empty results.

Required Fixes

Check the results.Status property

The response from GetReadResultAsync includes a status property.

Possible values: notStarted , running , succeeded , failed .

You must wait until the status is succeeded before processing results.

This ensures you don’t attempt to read lines before OCR has completed.

This corresponds to B.

Wrap in a loop with delay

Since OCR takes time, you need to poll the service until the status becomes succeeded or failed .

A typical pattern is:

ReadOperationResult results;

do

{

results = await client.GetReadResultAsync(Guid.Parse(operationId));

await Task.Delay( 1000 ); // wait 1 second before retrying

}

while (results.Status == OperationStatusCodes.Running || results.Status == OperationStatusCodes.NotStarted);

This corresponds to D.

Option Analysis

A. Remove the Guid.Parse(operationId) parameter

Incorrect. The operationId is required to fetch the OCR results.

B. Add code to verify the results.Status value

Correct. You must check whether the operation has completed.

C. Add code to verify the status of the txtHeaders.Status value

Incorrect. txtHeaders only contains metadata and the operation location. The OCR completion status comes from the results.Status in the GetReadResultAsync response, not from txtHeaders .

D. Wrap the call to GetReadResultAsync within a loop that contains a delay

Correct. This is how you poll until the operation has finished.

Correct Answer: B and D

Microsoft References

Azure Computer Vision Read API

Read text using the Computer Vision client library

Scenario Recap:

IoT data from 100 machines × 50 sensors × 1-minute intervals for 1 year = 5,000 time series datasets .

Requirement: Detect unusual values (outliers) to predict failures.

Correct Service:

Azure Anomaly Detector (A) is designed for time-series anomaly detection.

It learns temporal patterns and detects anomalies in sensor/IoT data streams.

Other options:

Cognitive Search = full-text search

Form Recognizer = extract text/fields from documents

Custom Vision = image classification

Answer: A. Anomaly Detector

Box 1: Yes

You create property accessors using the CreateProperty method that provides a handle to the BotState object. Each state property accessor allows you to get or set the value of the associated state property.

Box 2: Yes

Box 3: No

Before you exit the turn handler, you use the state management objects ' SaveChangesAsync() method to write all state changes back to storage.

The statement is:

" When using the Azure Cosmos DB Gremlin API, the container resource type is projected as a ______. "

Options:

graph → Correct. The Gremlin API in Azure Cosmos DB is designed to work with graph data models, supporting vertices (nodes) and edges (relationships). A container is projected as a graph.

table → Used when working with the Table API (key/value store). Not correct here.

partition key → Refers to data distribution and scalability, not the container resource type.

document → Refers to the SQL API or MongoDB API in Cosmos DB, not Gremlin.

Therefore, the correct answer is graph.

Correct Answer: graph

Microsoft References

Azure Cosmos DB Gremlin API

Azure Cosmos DB APIs and data models

Upload to: An Azure Storage account

Model type: Custom neural

You have 1,000 scanned hand-written survey responses with no consistent layout. The goal is to extract data while minimizing development effort.

Step 1: Upload location

For Azure AI Document Intelligence (formerly Form Recognizer), training data (images, PDFs) must be placed in a container in an Azure Storage account.

Options like Cosmos DB or Azure Files share are not valid training data sources for Document Intelligence.

Therefore, you upload the survey images to Azure Storage account.

Step 2: Model type

The surveys are handwritten and do not have a consistent layout.

Custom template models work only when the layout is fixed and consistent (e.g., invoices with the same fields in the same place).

Identity document (ID) model is a prebuilt model for passports, driver’s licenses, etc., not for surveys.

Custom neural model is designed to handle unstructured or variable-layout forms, including handwritten content. This best fits the survey scenario.

Thus, the correct configuration is:

Upload to Azure Storage account

Use Custom neural model

Correct Answer:

Upload to: An Azure Storage account

Model type: Custom neural

Microsoft References

Azure AI Document Intelligence – Custom models

Custom neural vs custom template models

Train a custom model with Azure Storage input

The Text Moderation API of Azure Content Moderator is specifically used for scanning text to detect potentially inappropriate or undesired content.

Key features include:

Adult classification score → Indicates the likelihood that the text contains adult content.

Racy classification score → Indicates the likelihood that the text contains sexually suggestive but not explicit content.

PII detection (personal data) is part of text moderation but is not always required when focusing strictly on enabling content moderation for chatbot text safety.

OCR is for extracting text from images, not for moderating chatbot conversations.

Text classification in this context refers to general machine learning categorization (not part of Content Moderator’s moderation API).

Thus, the two service responses directly tied to text moderation safety are:

Adult classification score

Racy classification score

Correct Answer for Q185: A and E

Microsoft Reference

Azure Content Moderator text moderation overview