A developer is integrating Azure OpenAI into a web application. They have deployed a gpt-4o model and are using the API key for authentication. They want to move to a more secure authentication method. What should they do?

Continue using the API key but store it in a configuration file

Use the Azure Management API to authenticate the web application

Use Azure AD authentication with a managed identity for the web application

Use the deployment name as a shared secret

A company is building a multilingual customer support chatbot. They need the chatbot to respond in the same language as the user's input. They have deployed a gpt-4o model. What should they do to ensure the chatbot responds in the correct language?

Include an instruction in the system message that tells the model to respond in the same language as the user's input

Deploy a separate model for each language

Set the temperature to 0 to force the model to use the user's language

Use the Azure AI Translator service to translate the model's responses

A customer service team wants to use Azure OpenAI to draft polite responses to customer emails. They need the model to maintain a consistent tone and follow company guidelines. What should they do when submitting prompts?

Send the email content as an image to a text-embedding model

Include the company's tone guidelines in the system message and provide the email content in the user message

Provide only the email content without any instructions

Use a DALL-E 3 deployment to generate text responses

Microsoft Certified:Azure AI Engineer Associate

Domain 2Objective 2

Use Azure OpenAI in Foundry Models to Generate Content AI-102 Practice Questions (Page 10)

Part of the Implement generative AI solutions domain, which accounts for 15-20% of the AI-102 exam. Microsoft does not publish an official question count, but from its 100-minute exam (~40–65 total, ~6–13 in this domain), expect 2–4 from this objective — we provide 49 practice questions to prepare you well beyond it. (estimate)

49questions here

10free pages

8concepts

15-20%of the exam

Questions 46–49

46expert · hard
A developer is integrating Azure OpenAI into a web application. They have deployed a gpt-4o model and are using the API key for authentication. They want to move to a more secure authentication method. What should they do?
Select an answer first
47foundation · easy
Which Azure OpenAI model is specifically designed to generate code from natural language prompts?
Select an answer first
48expert · hard
A company is building a multilingual customer support chatbot. They need the chatbot to respond in the same language as the user's input. They have deployed a gpt-4o model. What should they do to ensure the chatbot responds in the correct language?
Select an answer first
49application · medium
A customer service team wants to use Azure OpenAI to draft polite responses to customer emails. They need the model to maintain a consistent tone and follow company guidelines. What should they do when submitting prompts?
Select an answer first

Finished these 4 questions?

Review the revealed explanations, or continue through the curriculum.

No more pagesBack to AI-102

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Microsoft. “AI-102” is a trademark of its owner, used for identification only.

Use Azure OpenAI in Foundry Models to Generate Content AI-102 Practice Questions (Page 10)

Questions 46–49

A developer is integrating Azure OpenAI into a web application. They have deployed a gpt-4o model and are using the API key for authentication. They want to move to a more secure authentication method. What should they do?

Which Azure OpenAI model is specifically designed to generate code from natural language prompts?

A company is building a multilingual customer support chatbot. They need the chatbot to respond in the same language as the user's input. They have deployed a gpt-4o model. What should they do to ensure the chatbot responds in the correct language?

A customer service team wants to use Azure OpenAI to draft polite responses to customer emails. They need the model to maintain a consistent tone and follow company guidelines. What should they do when submitting prompts?

Keep studying — Implement generative AI solutions