Newly Released Microsoft AI-102 Exam PDF

You created five bots with Microsoft Bot Framework Composer, but want to make them appear as one unified bot for users, with dynamic routing depending on user input.

This is exactly the Bot Framework Orchestrator scenario. Orchestrator is the recognizer that allows you to dispatch incoming utterances to the correct skill (bot) or dialog.

Step 1 – Install Orchestrator package

To use Orchestrator inside Bot Framework Composer, you first install the Orchestrator package.

This provides the functionality for language understanding and routing.

Correct answer: F.

Step 2 – Change Recognizer/Dispatch type

By default, a bot project might use LUIS recognizer or Regex recognizer.

To use Orchestrator, you need to change the recognizer type to Orchestrator in Composer.

Correct answer: B.

Step 3 – Create an Orchestrator model

Orchestrator requires a trained model that maps utterances to intents or routes them to the correct skill/bot.

You must create an Orchestrator model for dispatch.

Correct answer: A.

Other Options (Incorrect):

C. Create a Composer extension → Not required for orchestrating multiple bots.

D. Enable WebSockets → Useful for streaming scenarios, not for bot orchestration.

E. Create a custom recognizer JSON file → Applies to building custom recognizers, not needed with Orchestrator.

The chatbot needs to recognize two different kinds of information:

Code names for internal product development

These are not standard entities like " locations " or " organizations " that prebuilt NER can detect.

You need to train a custom model to recognize internal terms or codenames (for example, " Project Falcon " ).

The correct Azure Cognitive Service for Language feature is Custom Named Entity Recognition (Custom NER), which allows defining and training entity categories specific to your business.

Messages that include credit card numbers

Credit card numbers are sensitive data falling under Personally Identifiable Information (PII).

Azure Cognitive Service for Language provides a PII detection feature that automatically identifies and masks sensitive information such as credit card numbers, SSNs, and phone numbers.

This minimizes development effort since it is prebuilt and ready to use.

Correct Answer Mapping:

Identify code names for internal product development → Custom named entity recognition (NER)

Identify messages that include credit card numbers → Personally Identifiable Information (PII) detection

Microsoft References

Custom Named Entity Recognition in Azure AI Language

PII detection in Azure AI Language

Scenario Recap

You have a web app app1 running on VM1 in vnet1.

You plan to create an Azure Cognitive Search service (service1).

Goal: Ensure app1 can connect to service1 without routing over the public internet.

Proposed Solution

“You deploy service1 and a public endpoint to a new virtual network, and you configure Azure Private Link.”

Analysis

Azure Cognitive Search and Private Link:

Azure Cognitive Search supports Private Endpoints via Azure Private Link.

When you configure a private endpoint, the service is accessible privately over the virtual network and traffic does not go over the public internet.

You can still keep a public endpoint enabled optionally, but access from your VM can be restricted to the private endpoint.

Key Point: The solution specifies using a public endpoint AND a private link.

This still meets the requirement because Private Link ensures that VM1 in vnet1 communicates with service1 privately.

The existence of the public endpoint does not force traffic to go public — traffic from the private endpoint is routed over the VNet.

Conclusion

Yes, this solution meets the goal because Private Link provides secure, private connectivity to Cognitive Search, avoiding the public internet.

Correct Answer: A. Yes

Microsoft References

Secure access to Azure Cognitive Search with Private Link

Azure Private Link overview

Use " definition " for the first field and " sampleBlobUrl " for the second field

When creating a custom text category in Azure AI Content Safety, you call the PUT /contentsafety/text/categories/{categoryName} endpoint and provide a JSON body that includes:

categoryName : the identifier of your category.

definition : a natural-language description of what the category covers (e.g., “text prompts about learning advice while preparing for an exam”).

sampleBlobUrl : a pointer to labeled sample data (typically a JSONL file in Azure Storage) used to help the service understand the category.

Keys like prompt or text are used when analyzing content (for example, text:detect ), not when defining a category. Likewise, blocklistName applies to blocklist operations, and outputType is not part of the category-creation schema. Therefore, the correct payload fields to complete the cURL are definition and sampleBlobUrl .

Microsoft Azure AI References (titles only)

Azure AI Content Safety – Create or update custom text categories (REST)

Azure AI Content Safety – Custom categories concepts and training data (JSONL in blob storage)

Azure AI Content Safety – Text analysis vs. category management endpoints