Cisco
CompTIA
ISC
EC-Council
EXIN
Fortinet
ITIL
Juniper
Microsoft
VMware
Avaya
SAP
Google
NVIDIA
Salesforce
Amazon
Palo Alto Networks
ISC2
Splunk
ServiceNow
All Vendors
  2. Home
  3. Exams
  4. Microsoft
  5. AI-102

Microsoft AI-102 Exam Questions
Designing and Implementing a Microsoft Azure AI Solution (Page 11 )

Updated On: 21-Feb-2026
Page 11 of 61
PDF with 367 Questions

You have an app that analyzes images by using the Computer Vision API.

You need to configure the app to provide an output for users who are vision impaired. The solution must provide the output in complete sentences.

Which API call should you perform?

  1. readInStreamAsync
  2. analyzeImagesByDomainInStreamAsync
  3. tagImageInStreamAsync
  4. describeImageInStreamAsync

Answer(s): D

Explanation:

describeImageInStreamAsync
This operation generates a description of an image in human readable language with complete sentences. The description is based on a collection of content tags, which are also returned by the operation. More than one description can be generated for each image. Descriptions are ordered by their confidence score. Descriptions may include results from celebrity and landmark domain models, if applicable. Two input methods are supported (1) Uploading an image or (2) specifying an image URL. A successful response will be returned in JSON. If the request failed, the response will contain an error code and a message to help understand what went wrong.

Incorrect:
* tagImageInStreamAsync
This operation generates a list of words, or tags, that are relevant to the content of the supplied image. The Computer Vision API can return tags based on objects, living beings, scenery or actions found in images. Unlike categories, tags are not organized according to a hierarchical classification system, but correspond to image content. Tags may contain hints to avoid ambiguity or provide context, for example the tag "ascomycete" may be accompanied by the hint "fungus". Two input methods are supported (1) Uploading an image or (2) specifying an image URL. A successful response will be returned in JSON. If the request failed, the response will contain an error code and a message to help understand what went wrong.

* ReadInStreamAsync
There is a ComputerVisionClientExtensions.ReadInStreamAsync method.
Use this interface to get the result of a Read operation, employing the state-of-the-art Optical Character Recognition (OCR) algorithms optimized for text-heavy documents. When you use the Read interface, the response contains a field called 'Operation-Location'. The 'Operation-Location' field contains the URL that you must use for your 'GetReadResult' operation to access OCR results.


Reference:

https://learn.microsoft.com/en-us/java/api/com.microsoft.azure.cognitiveservices.vision.computervision.computervision



DRAG DROP (Drag and Drop is not supported)
You have a Custom Vision service project that performs object detection. The project uses the General domain for classification and contains a trained model.

You need to export the model for use on a network that is disconnected from the internet.

Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.
Select and Place:

  1. See Explanation section for answer.

Answer(s): A

Explanation:



Step 1: Change the Domains to General (compact)
Select a domain for a Custom Vision project, Compact domains
The models generated by compact domains can be exported to run locally.

Step 2: Retrain the model.

Step 3: Export the model

Note: Example
Use a TensorFlow model exported from Azure Custom Vision
Azure Custom Vision Service lets you export your image classification and object detection models to run locally on a device. For example, you can utilize the exported models in mobile applications or run a model in a microcontroller to deploy a Computer Vision application at the edge.

Select a compact domain
In this section, you will convert the domain of your existing Custom Vision model to a compact one.

If you have already trained a Custom Vision model using a compact domain, you can skip the following steps.

1. Sign in to the Custom Vision web portal and select your project.

2. Then, click on the settings icon (⚙) at the top toolbar to view the project settings.

3. Under Domains, select one of the Compact domains and click Save Changes. (Step 1)

4. Select the Train button to train the model using the new domain. (Step 2)

5. Export the model (Step 3)


Reference:

https://learn.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/select-domain
https://sfoteini.github.io/blog/use-a-tensorflow-model-exported-from-azure-custom-vision/



You are building an AI solution that will use Sentiment Analysis results from surveys to calculate bonuses for customer service staff.

You need to ensure that the solution meets the Microsoft responsible AI principles.
What should you do?

  1. Add a human review and approval step before making decisions that affect the staff's financial situation.
  2. Include the Sentiment Analysis results when surveys return a low confidence score.
  3. Use all the surveys, including surveys by customers who requested that their account be deleted and their data be removed.
  4. Publish the raw survey data to a central location and provide the staff with access to the location.

Answer(s): A



You have an Azure subscription that contains a Language service resource named ta1 and a virtual network named vnet1.

You need to ensure that only resources in vnet1 can access ta1.
What should you configure?

  1. a network security group (NSG) for vnet1
  2. Azure Firewall for vnet1
  3. the virtual network settings for ta1
  4. a Language service container for ta1

Answer(s): C


Reference:

https://learn.microsoft.com/en-us/azure/cognitive-services/cognitive-services-virtual-networks?tabs=portal



You are developing a monitoring system that will analyze engine sensor data, such as rotation speed, angle, temperature, and pressure. The system must generate an alert in response to atypical values.

What should you include in the solution?

  1. Application Insights in Azure Monitor
  2. metric alerts in Azure Monitor
  3. Multivariate Anomaly Detection
  4. Univariate Anomaly Detection

Answer(s): C

Explanation:

The Multivariate Anomaly Detection APIs further enable developers by easily integrating advanced AI for detecting anomalies from groups of metrics, without the need for machine learning knowledge or labeled data.


Reference:

https://learn.microsoft.com/en-us/azure/cognitive-services/anomaly-detector/overview#multivariate-anomaly-detection






Post your Comments and Discuss Microsoft AI-102 exam dumps with other Community members:

Join the AI-102 Discussion