Build generative applications by using Foundry
11 practice questions under this official exam objective (AI-103), each with the answer key, an option-by-option explanation and instant feedback.
Questions under this objective
11 total · page 1 of 1Mitigating Indirect Prompt Injection in Multimodal AI
Learn why configuring a prompt shield for user prompts fails to protect against hidden instructions in uploaded images. The correct answer is No (B),
Which Request Parameters Maximize Foundry Output Stability and Reasoning?
This hotspot asks which Python request parameters to change for a deployed Foundry chat model so automated validation stops failing on minor wording d
Azure AI Services Multi-Service Resource Creation
This scenario tests the correct Azure REST API parameters for creating a multi-service AI resource. The solution requires using PUT for creation and s
Improving Summary Completeness With a Reflection Pass
To improve summary completeness in a Microsoft Foundry agent within application code, add a reflection pass that drafts, critiques, and expands the su
Choosing the Foundry Model for Generative Text Suggestions
This AI-103 question tests model selection in Microsoft Foundry: suggesting product names from a description is a text-generation task, so the correct
Moderate Input Text Against a Custom Blocklist in Foundry
This AI-103 hotspot tests Content Safety custom blocklist moderation from Python. The answer is an AnalyzeTextOptions request with text, blocklist_nam
Polling Azure Vision Read OCR until it completes
Azure Vision Read OCR results are fetched asynchronously, so get_read_result returns before analysis finishes. The correct fix is to check read_result
How Should Foundry Chat Playground Explain Code at Lowest Cost?
This AI-103 scenario tests how to ask the Foundry Chat playground to explain JavaScript code while minimizing token spend. The correct approach is a b
Azure AI Custom Vision for Defective Product Detection
Azure AI Custom Vision is the optimal service for training custom image classification models with minimal development effort. This solution leverages
Context Steering in Foundry LLM Applications
This scenario tests the implementation of context steering to ensure Large Language Models provide accurate definitions for ambiguous terms like 'LLM'
Configuring Azure Custom Vision for Image Classification
Learn how to configure Azure Custom Vision projects for image classification tasks, specifically distinguishing between multiclass and object detectio