AI Engineer: Designing and Implementing an Azure [AI-100] 3 — Questions and Answers
Question 1: You are building a knowledge-mining solution. Which Azure service allows you to use AI enrichment skills (OCR, entity extraction) during indexing of documents?
- Azure Synapse Analytics
- Azure Cognitive Search with AI enrichment (Correct answer)
- Azure Data Factory
- Azure Stream Analytics
Correct answer: Azure Cognitive Search with AI enrichment
Azure Cognitive Search supports AI enrichment pipelines called skillsets that apply cognitive skills during document indexing.
Question 2: A custom vision model trained in Azure Custom Vision needs to run on an IoT Edge device without internet connectivity. What should you do?
- Export the model as a Docker container and deploy it to IoT Edge (Correct answer)
- Use the Custom Vision prediction endpoint directly from the device
- Copy the model weights to Azure Blob and reference them
- Deploy the model to Azure Functions
Correct answer: Export the model as a Docker container and deploy it to IoT Edge
Azure Custom Vision supports exporting trained models as Docker containers for offline deployment on edge devices.
Question 3: You need to build a multi-turn conversational bot that maintains context across turns. Which bot framework capability enables this?
- Adaptive Cards
- Dialog state management (Correct answer)
- Bot Channel Registration
- Direct Line Speech
Correct answer: Dialog state management
Dialog state management in the Bot Framework SDK persists conversation state across multiple turns.
Question 4: Which pricing tier of Azure Cognitive Services provides a Service Level Agreement (SLA) guarantee?
- Free (F0) tier
- Standard (S) tier (Correct answer)
- Both Free and Standard tiers
- Neither tier includes an SLA
Correct answer: Standard (S) tier
Only the Standard (S) paid tier of Azure Cognitive Services includes SLA commitments; the Free tier does not.
Question 5: Your team wants to monitor model drift for a deployed Azure Machine Learning model over time. Which feature should you use?
- Azure Monitor Alerts
- Data drift detection in Azure Machine Learning (Correct answer)
- Azure Application Insights custom events
- Azure Advisor recommendations
Correct answer: Data drift detection in Azure Machine Learning
Azure Machine Learning's data drift detection compares incoming scoring data against the training dataset to identify distribution shifts.
Question 6: You need to identify the language of text submitted by users before routing it to language-specific processing pipelines. Which Azure Text Analytics feature handles this?
- Named Entity Recognition
- Language detection (Correct answer)
- Sentiment analysis
- Key phrase extraction
Correct answer: Language detection
The language detection feature of Azure Text Analytics identifies the dominant language of input text.
Question 7: An Azure AI solution must comply with GDPR requirements. Which Azure Cognitive Services feature helps you find and redact personally identifiable information (PII) in text?
- Content Moderator text moderation
- Text Analytics PII detection and redaction (Correct answer)
- Azure Purview data catalog
- Azure Policy compliance
Correct answer: Text Analytics PII detection and redaction
Azure Text Analytics provides a PII detection feature that identifies and can redact sensitive personal information in text.
AI Engineer: Designing and Implementing an Azure [AI-100] 3
You are building a knowledge-mining solution.
Which Azure service allows you to use AI enrichment skills (OCR, entity extraction) during indexing of documents?