Microsoft AI-102 Exam (page: 1)
Microsoft Designing and Implementing a Azure AI Solution
Updated on: 28-Jul-2025

Viewing Page 1 of 67

DRAG DROP (Drag and Drop is not supported)
You have 100 chatbots that each has its own Language Understanding model.
Frequently, you must add the same phrases to each model.
You need to programmatically update the Language Understanding models to include the new phrases.
How should you complete the code? To answer, drag the appropriate values to the correct targets. Each value 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.
Select and Place:

  1. See Explanation section for answer.

Answer(s): A

Explanation:


Box 1: AddPhraseListAsync
Example: Add phraselist feature
var phraselistId = await client.Features.AddPhraseListAsync(appId, versionId, new PhraselistCreateObject
{
EnabledForAllModels = false,
IsExchangeable = true,
Name = "QuantityPhraselist",
Phrases = "few,more,extra"
});
Box 2: PhraselistCreateObject


Reference:

https://docs.microsoft.com/en-us/azure/cognitive-services/luis/client-libraries-rest-api



DRAG DROP (Drag and Drop is not supported)
You plan to use a Language Understanding application named app1 that is deployed to a container.
App1 was developed by using a Language Understanding authoring resource named lu1.
App1 has the versions shown in the following table.
You need to create a container that uses the latest deployable version of app1.
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: Export the model using the Export for containers (GZIP) option.
Export versioned app's package from LUIS portal
The versioned app's package is available from the Versions list page.
1. Sign on to the LUIS portal.
2. Select the app in the list.
3. Select Manage in the app's navigation bar.
4. Select Versions in the left navigation bar.
5. Select the checkbox to the left of the version name in the list.
6. Select the Export item from the contextual toolbar above the list.
7. Select Export for container (GZIP).
8. The package is downloaded from the browser.

Step 2: Select v1.1 of app1.
A trained or published app packaged as a mounted input to the container with its associated App ID.
Step 3: Run a contain and mount the model file.
Run the container, with the required input mount and billing settings.


Reference:

https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-container-howto



You need to build a chatbot that meets the following requirements:
-Supports chit-chat, knowledge base, and multilingual models
-Performs sentiment analysis on user messages
-Selects the best language model automatically
What should you integrate into the chatbot?

  1. QnA Maker, Language Understanding, and Dispatch
  2. Translator, Speech, and Dispatch
  3. Language Understanding, Text Analytics, and QnA Maker
  4. Text Analytics, Translator, and Dispatch

Answer(s): C

Explanation:

Language Understanding: An AI service that allows users to interact with your applications, bots, and IoT devices by using natural language.
QnA Maker is a cloud-based Natural Language Processing (NLP) service that allows you to create a natural conversational layer over your data. It is used to find the most appropriate answer for any input from your custom knowledge base (KB) of information.
Text Analytics: Mine insights in unstructured text using natural language processing (NLP)ג€"no machine learning expertise required. Gain a deeper understanding of customer opinions with sentiment analysis. The Language Detection feature of the Azure Text Analytics REST API evaluates text input
Incorrect Answers:
A, B, D: Dispatch uses sample utterances for each of your bot's different tasks (LUIS, QnA Maker, or custom), and builds a model that can be used to properly route your user's request to the right task, even across multiple bots.


Reference:

https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics/ https://docs.microsoft.com/en-us/azure/cognitive-services/qnamaker/overview/overview



Your company wants to reduce how long it takes for employees to log receipts in expense reports. All the receipts are in English.
You need to extract top-level information from the receipts, such as the vendor and the transaction total. The solution must minimize development effort.
Which Azure service should you use?

  1. Custom Vision
  2. Personalizer
  3. Form Recognizer
  4. Computer Vision

Answer(s): C

Explanation:

Azure Form Recognizer is a cognitive service that lets you build automated data processing software using machine learning technology. Identify and extract text, key/value pairs, selection marks, tables, and structure from your documentsג€"the service outputs structured data that includes the relationships in the original file, bounding boxes, confidence and more.
Form Recognizer is composed of custom document processing models, prebuilt models for invoices, receipts, IDs and business cards, and the layout model.


Reference:

https://docs.microsoft.com/en-us/azure/cognitive-services/form-recognizer



HOTSPOT (Drag and Drop is not supported)
You need to create a new resource that will be used to perform sentiment analysis and optical character recognition (OCR). The solution must meet the following requirements:
-Use a single key and endpoint to access multiple services.
-Consolidate billing for future services that you might use.
-Support the use of Computer Vision in the future.
How should you complete the HTTP request to create the new resource? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Hot Area:

  1. See Explanation section for answer.

Answer(s): A

Explanation:


Box 1: PUT
Sample Request: PUT https://management.azure.com/subscriptions/00000000-0000-0000-0000-000000000000/resourceGroups/test-rg/providers/
Microsoft.DeviceUpdate/accounts/contoso?api-version=2020-03-01-preview
Incorrect Answers:
PATCH is for updates.
Box 2: CognitiveServices
Microsoft Azure Cognitive Services provide us to use its pre-trained models for various Business Problems related to Machine Learning.
List of Different Services are:
- Decision
- Language (includes sentiment analysis)
- Speech
- Vision (includes OCR)
- Web Search


Reference:

https://docs.microsoft.com/en-us/rest/api/deviceupdate/resourcemanager/accounts/create https://www.analyticsvidhya.com/blog/2020/12/microsoft-azure-cognitive-services-api-for-ai-development/



Viewing Page 1 of 67



Share your comments for Microsoft AI-102 exam with other users:

Lele 11/20/2023 11:55:00 AM

does anybody know if are these real exam questions?
EUROPEAN UNION


Girish Jain 10/9/2023 12:01:00 PM

are these questions similar to actual questions in the exam? because they seem to be too easy
Anonymous


Phil 12/8/2022 11:16:00 PM

i have a lot of experience but what comes in the exam is totally different from the practical day to day tasks. so i thought i would rather rely on these brain dumps rather failing the exam.
GERMANY


BV 6/8/2023 4:35:00 AM

good questions
NETHERLANDS


krishna 12/19/2023 2:05:00 AM

valied exam dumps. they were very helpful and i got a pretty good score. i am very grateful for this service and exam questions
Anonymous


Pie 9/3/2023 4:56:00 AM

will it help?
INDIA


Lucio 10/6/2023 1:45:00 PM

very useful to verify knowledge before exam
POLAND


Ajay 5/17/2023 4:54:00 AM

good stuffs
Anonymous


TestPD1 8/10/2023 12:19:00 PM

question 17 : responses arent b and c ?
EUROPEAN UNION


Nhlanhla 12/13/2023 5:26:00 AM

just passed the exam on my first try using these dumps.
Anonymous


Rizwan 1/6/2024 2:18:00 AM

very helpful
INDIA


Yady 5/24/2023 10:40:00 PM

these questions look good.
SINGAPORE


Kettie 10/12/2023 1:18:00 AM

this is very helpful content
Anonymous


SB 7/21/2023 3:18:00 AM

please provide the dumps
UNITED STATES


David 8/2/2023 8:20:00 AM

it is amazing
Anonymous


User 8/3/2023 3:32:00 AM

quesion 178 about "a banking system that predicts whether a loan will be repaid is an example of the" the answer is classification. not regresion, you should fix it.
EUROPEAN UNION


quen 7/26/2023 10:39:00 AM

please upload apache spark dumps
Anonymous


Erineo 11/2/2023 5:34:00 PM

q14 is b&c to reduce you will switch off mail for every single alert and you will switch on daily digest to get a mail once per day, you might even skip the empty digest mail but i see this as a part of the daily digest adjustment
Anonymous


Paul 10/21/2023 8:25:00 AM

i think it is good question
Anonymous


Unknown 8/15/2023 5:09:00 AM

good for students who wish to give certification.
INDIA


Ch 11/20/2023 10:56:00 PM

is there a google drive link to the images? the links in questions are not working.
AUSTRALIA


Joey 5/16/2023 5:25:00 AM

very promising, looks great, so much wow!
Anonymous


alaska 10/24/2023 5:48:00 AM

i scored 87% on the az-204 exam. thanks! i always trust
GERMANY


nnn 7/9/2023 11:09:00 PM

good need more
Anonymous


User-sfdc 12/29/2023 7:21:00 AM

sample questions seems good
Anonymous


Tamer dam 8/4/2023 10:21:00 AM

huawei is ok
UNITED STATES


YK 12/11/2023 1:10:00 AM

good one nice
JAPAN


de 8/28/2023 2:38:00 AM

please continue
GERMANY


DMZ 6/25/2023 11:56:00 PM

this exam dumps just did the job. i donot want to ruffle your feathers but your exam dumps and mock test engine is amazing.
UNITED KINGDOM


Jose 8/30/2023 6:14:00 AM

nice questions
PORTUGAL


Tar01 7/24/2023 7:07:00 PM

the explanation are really helpful
Anonymous


DaveG 12/15/2023 4:50:00 PM

just passed my exam yesterday on my first attempt. these dumps were extremely helpful in passing first time. the questions were very, very similar to these questions!
Anonymous


A.K. 6/30/2023 6:34:00 AM

cosmos db is paas not saas
Anonymous


S Roychowdhury 6/26/2023 5:27:00 PM

what is the percentage of common questions in gcp exam compared to 197 dump questions? are they 100% matching with real gcp exam?
Anonymous