Online Access Free AI-103 Practice Test

A multimodal agent processes user-uploaded images. An attacker embeds hidden text instructions inside an image, hoping the agent will read and act on them. Which Azure AI Content Safety capability is designed to detect this kind of attack?

• A.Prompt Shields, which detects document and indirect prompt injection
• B.Raising the image resolution threshold on the analyser
• C.Disabling the agent's file search tool
• D.A content filter set to High severity for the Violence category

You have an Azure subscription that contains an Azure OpenAI resource.
You need to build an app that will suggest product names from a given product description.
Which model should you use?

• A.embeddings
• B.GPT-4
• C.DALL-E
• D.Whisper

You have an application that processes scanned PDF invoices. The invoices have varied layouts and include multipage tables.
You have a pipeline that uses optical character recognition (OCR) and extracts totals and invoice numbers. The results are often incorrect because the document structure is ignored.
You need to implement a solution that provides OCR, layout analysis, and template-generalizing field extraction. The solution must NOT require training a custom model. The solution must minimize administrative effort.
What should you include in the solution?

• A.Azure Content Understanding in Foundry Tools
• B.an Azure Machine Learning model
• C.Azure Language in Foundry Tools

You are building a voice agent for a pharmacy. It must accept spoken questions, reply with synthesised speech, and accurately recognise specialised medicine names that a general speech model often mishears. Which capability should you configure?

• A.Azure AI Document Intelligence on the audio stream
• B.A custom speech model for speech-to-text within the agent
• C.Azure Translator to convert the audio
• D.Only the default text-to-speech voice

A copilot must answer multi-part questions that depend on earlier turns in the conversation. You want the system to break each complex question into focused subqueries, run them in parallel, and semantically rerank the results before composing an answer. Which Azure AI Search capability provides this?

• A.Agentic retrieval
• B.Increasing the top-k value on a single keyword query
• C.Classic keyword search with a scoring profile
• D.A single vector query with a high similarity threshold