AI-102 Exam Dumps - Designing and Implementing a Microsoft Azure AI Solution

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

You need to restrict access to an Azure AI services (Cognitive Services) account so that only specific resources on a virtual network can reach it and block public (external) access with minimum effort.

The simplest approach is to use Virtual Network service endpoints for Microsoft.CognitiveServices:

Enable the service endpoint on the VNet/subnet (VNet1) for Microsoft.CognitiveServices

This routes traffic from that subnet to the Cognitive Services account over the Azure backbone and allows the account to identify traffic coming from that subnet.

Modify the Cognitive Services account’s network settings (CSAccount1)

Set Public network access: Disabled (or allow access from Selected networks) and add the VNet/subnet enabled with the service endpoint to the allowed list.

This blocks all external access while permitting access from only the specified VNet resources.

Other options are not appropriate:

A. Modify VNet settings (generic) doesn’t target the required service endpoint action.

C. IAM controls user/role authorization, not network access.

D. Create a virtual subnet isn’t necessary if the VNet/subnet already exists; using service endpoints avoids creating/maintaining private endpoints.

Therefore, the correct pair is B and E.

Microsoft Azure AI Solution References

Secure Cognitive Services with virtual network service endpoints – explains enabling Microsoft.CognitiveServices service endpoints on a subnet and restricting the account to selected networks.

https://learn.microsoft.com/azure/ai-services/cognitive-services-virtual-networks

Network access restrictions for Cognitive Services – details configuring “Public network access” and allowing access from selected VNets/subnets.

https://learn.microsoft.com/azure/ai-services/cognitive-services-network-security

Overview of securing Azure AI services – covers options (service endpoints vs. private endpoints) and minimal configuration steps.

https://learn.microsoft.com/azure/ai-services/security-networking

A. True

B. True

C. True

B: see this example code from documentation that uses PersonGroup of size 10,000 :

https://docs.microsoft.com/en-us/azure/cognitive-services/face/face-api-how-to-topics/how-to-add-faces

the question wants to trick you into thinking you need to use a LargePersonGroup for a size of 10,000 - but the documentation for it doesn ' t include this limitation or criteria: https://docs.microsoft.com/en-us/azure/cognitive-services/face/face-api-how-to-topics/how-to-use-large-scale

To detect common data types such as temperatures, currency values, email addresses, and telephone numbers with minimal development effort, you should use pre-built entity components in Conversational Language Understanding (CLU). Prebuilt components are ready-made recognizers that automatically extract well-known patterns from utterances—no training, labeling, lists, or regex authoring required.

Specifically, CLU offers the following relevant prebuilt components:

Quantity.Temperature – extracts temperatures (e.g., “34 degrees celsius”).

Quantity.Currency – extracts monetary amounts and currency units (e.g., “$20”, “£15.50”).

Email – extracts email addresses.

Phone Number – extracts phone numbers.

These components are designed to be dropped into your entities and immediately provide predictions, which minimizes development effort compared to:

List entities (you must curate values/synonyms yourself),

Learned entities (require labeling utterances and training),

Regular expression components (you must craft and maintain regex patterns), or

Utterances (training data, not a capability for detection by itself).

Microsoft References

Supported prebuilt entity components in CLU (shows Quantity.Temperature, Quantity.Currency, Email, Phone Number, etc.). Microsoft Learn

Entity components in CLU (explains prebuilt, learned, list, and regex components and why prebuilt components are automatically detected). Microsoft Learn

Scenario Recap:

Application: Flower classification.

Solution: Add new images and labels to the existing model. Retrain and publish the model.

Analysis:

This is the best practice workflow:

Add new labeled training images.

Retrain the model with updated dataset.

Publish the retrained model.

This clearly meets the goal.

Correct Answer: A. Yes

To extend Video Indexer with industry-specific terms, you upload a plain text (TXT) file containing the vocabulary.

PDF, XML, XLS are not supported for custom vocabulary upload.

Correct Answer: C

To make the chatbot respond only when the answer’s confidence is ≥ 95%, you must set the request body property confidenceScoreThreshold to 0.95 in the Query knowledge bases operation of Custom question answering. The REST API for querying a Custom question answering project is:

POST { Endpoint }/language/ :query-knowledgebases?projectName= {projectName} & deploymentName={deploymentName} & api-version= 2021 - 10 - 01

Here, projectName identifies the Custom question answering project you’re querying (the screenshot’s placeholder < chatbot-project > ), while deploymentName specifies which deployment (for example, production ) to use. The request body includes confidenceScoreThreshold (0–1) to filter out answers below that score; setting it to 0.95 enforces the requirement.

Example snippet:

curl -X POST " $LANGUAGE_ENDPOINT /language/:query-knowledgebases?projectName= < chatbot-project > & deploymentName=production & api-version=2021-10-01 " \

-H " Ocp-Apim-Subscription-Key: $LANGUAGE_KEY " \

-H " Content-Type: application/json " \

-d ' {

" question " : " How much energy does my phone have left? " ,

" confidenceScoreThreshold " : 0.95

} '

References

REST API: Question Answering – Get Answers (shows endpoint with projectName / deploymentName and the confidenceScoreThreshold request property). Microsoft Learn

REST API (newer version) parameter list for projectName / deploymentName . Microsoft Learn