Microsoft Updated AI-102 Exam Questions and Answers by sunny

To quickly improve a GPT-3.5 chatbot’s response quality with minimal development effort:

Provide grounding content (B): Ground the model with authoritative data (e.g., the travel agent’s policies, inventory, fares) using Azure OpenAI on your data or a lightweight RAG pattern. Grounding reduces hallucinations and makes answers more accurate and context-aware without retraining the model. This typically involves configuring a data connection (Azure Cognitive Search/Blob) and augmenting prompts—far less effort than training.

Add sample request/response pairs (C): Use few-shot examples directly in the system/user messages to demonstrate ideal answers, style, and formatting. Few-shot prompting is a core prompt-engineering technique that meaningfully boosts quality with minimal code changes or infrastructure.

Options A, D, and E involve model training or retraining (fine-tuning or building a custom LLM), which require data preparation, experimentation, monitoring, and higher cost/complexity—contrary to the “minimize development effort” constraint.

Microsoft References

Prompt engineering with examples (few-shot) to improve output quality:

https://learn.microsoft.com/azure/ai-services/openai/concepts/prompt-engineering

Azure OpenAI “on your data” (grounding to improve relevance and accuracy):

https://learn.microsoft.com/azure/ai-services/openai/concepts/use-your-data

Guidance comparing prompt engineering/grounding with fine-tuning and when to use each:

https://learn.microsoft.com/azure/ai-services/openai/concepts/fine-tuning

How-to: Fine-tuning (shows added complexity vs. prompt techniques):

https://learn.microsoft.com/azure/ai-services/openai/how-to/fine-tuning

To detect aggressive language (e.g., profanity/abuse) and sexually explicit content in text using the Content Moderator Text – Screen API:

classify = true

Enables machine-assisted text classification that returns category scores (e.g., sexually explicit/suggestive categories). This is required to identify sexual content.

language = < code > (for example, eng )

Specifies the language so profanity/abusive terms are detected correctly. The profanity detection in Text-Screen is language dependent.

autocorrect = true

Helps normalize intentionally misspelled or obfuscated words so that profanity or aggressive terms are still detected (e.g., “f@#$” → “fuck”).

Other parameters in the blade are not necessary for this goal:

PII targets personal data extraction, not aggression/sexuality.

listId is for matching against custom blocklists.

Headers like Ocp-Apim-Subscription-Key and Content-Type are required to call the API, but they are not the content-analysis settings that control detection behavior asked for in this question.

Microsoft Azure AI References

Azure AI Content Moderator – Screen text API parameters (autocorrect, language, classify) and category outputs.

Azure AI Content Moderator – Text moderation concepts: profanity detection and classification categories.

In Custom Question Answering (part of Azure AI Language), if you want to define alternative words or spellings for a specific term (e.g., testing , trials , evaluate ), you must use the alterations property.

Each alteration object contains a list of alternative values for the same meaning.

Example:

{

" alterations " : [

{

" alterations " : [

" testing " ,

" trials " ,

" evaluate "

]

}

]

}

phrases is used for pattern matching in question-answer pairs.

synonyms is used for synonyms within LUIS (Language Understanding), not for QnA alterations.

value is used inside synonyms definitions in some contexts but not here.

Correct JSON Payload Completion:

The JSON should be:

{

" alterations " : [

{

" alterations " : [

" testing " ,

" trials " ,

" evaluate "

]

}

]

}

Verified Answer:

Left box: " alterations "

Right box: " alterations "

Microsoft References:

Manage alterations in Custom Question Answering (Azure AI Language)

Authoring API reference for alterations