McAfee Secure

Exam Code: AI-901

Exam Name: Microsoft Azure AI Fundamentals

Certification Provider: Microsoft

Corresponding Certification: Microsoft Certified: Azure AI Fundamentals

Microsoft AI-901 Questions & Answers

Study with Up-To-Date REAL Exam Questions and Answers from the ACTUAL Test

166 Questions & Answers with Testing Engine

"Microsoft Azure AI Fundamentals Exam", also known as AI-901 exam, is a Microsoft certification exam.

Pass your tests with the always up-to-date AI-901 Exam Engine. Your AI-901 training materials keep you at the head of the pack!

Satisfaction Guaranteed

Money Back Guarantee

Testking provides hassle-free money back guarantee with our products. That is because we have 100% trust in the abilities of our professional and experience product team, and our record is a proof of that.

99.6% PASS RATE
Was: $137.49
Now: $124.99

Microsoft AI-901 Practice Test 33

Question 320

An Azure-based AI team must satisfy this objective: An insurance company wants to extract named policy limits from a contract. Which design choice is best?

  1. Create a schema for policy type, coverage amount and effective dates
  2. Enable a supported barcode extraction or recognition feature
  3. Use an appropriate Content Understanding or invoice-specific analyzer with a typed field schema
  4. Run supported image text extraction with field schema and source location

Explanation

Correct Answer

A:

Custom extraction maps semantically relevant phrases to typed fields. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

B:

A barcode is a structured visual symbol not ordinary OCR text. That is not sufficient here: Custom extraction maps semantically relevant phrases to typed fields.

C:

Document extraction turns unstructured pages into validated structured fields. That is not sufficient here: Custom extraction maps semantically relevant phrases to typed fields.

D:

Visual information extraction can map pixels to structured identifiers. That is not sufficient here: Custom extraction maps semantically relevant phrases to typed fields.

Question 321

An Azure AI Fundamentals solution has this requirement: A financial AI assistant uses undocumented features to decide transaction eligibility. Which implementation most directly addresses it?

  1. Maintain a governed feature inventory and trace decisions to policy
  2. Version procedures and limit grounding to the latest authorized operational guidance
  3. Exclude protected proxies from eligibility logic and test the remaining permitted factors
  4. Apply retention and deletion controls subject to recorded legal exceptions

Explanation

Correct Answer

A:

Accountability requires interpretable reasons for consequential decisions. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

B:

A precise explanation of an obsolete procedure can still be dangerous. That is not sufficient here: Accountability requires interpretable reasons for consequential decisions.

C:

Legitimate credit criteria cannot be replaced by sensitive identity traits. That is not sufficient here: Accountability requires interpretable reasons for consequential decisions.

D:

Accountability requires evidence of actual data lifecycle actions. That is not sufficient here: Accountability requires interpretable reasons for consequential decisions.

Question 322

An acceptance tester needs to validate: Use an agent workflow with a permitted ticket tool and an authorization gate. Which observed result proves the intended behavior?

  1. Held-out requests receive the appropriate routed intent labels
  2. The top ranked article matches the issue and is permitted for that customer
  3. Names in a labeled sample are detected and redacted
  4. A logged tool receipt proves a permitted ticket was created

Explanation

Correct Answer

D:

Agentic workloads combine reasoning and bounded external actions. The expected acceptance evidence is: A logged tool receipt proves a permitted ticket was created. This observation directly tests the stated behavior.

Incorrect Answers

A:

Classification maps text to one of several predefined categories. This observation does not establish the required result: A logged tool receipt proves a permitted ticket was created.

B:

Recommendations rank candidate items rather than simply generating arbitrary titles. This observation does not establish the required result: A logged tool receipt proves a permitted ticket was created.

C:

Entity extraction locates sensitive spans for privacy handling. This observation does not establish the required result: A logged tool receipt proves a permitted ticket was created.

Question 323

An Azure AI Fundamentals solution has this requirement: An AI note taker records customer conversations without explaining retention. Which implementation most directly addresses it?

  1. Restrict processing, inference, logs and backups to authorized regions
  2. Disclose collection purpose and retention period before capturing sensitive audio
  3. Minimize unnecessary identifying visual data and enforce approved access
  4. Require independent transaction authorization and approval outside prompts

Explanation

Correct Answer

B:

Privacy requires meaningful notice and bounded handling of personal data. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Privacy and compliance require controlling the full data path. That is not sufficient here: Privacy requires meaningful notice and bounded handling of personal data.

C:

Privacy applies to image content as well as text transcripts. That is not sufficient here: Privacy requires meaningful notice and bounded handling of personal data.

D:

Accountable high-impact operations need verifiable authorized signatures. That is not sufficient here: Privacy requires meaningful notice and bounded handling of personal data.

Question 324

An Azure-based AI team must satisfy this objective: A procurement inbox receives purchase orders, receipts and contracts. Which design choice is best?

  1. Check feature, model and regional availability before creating an analyzer
  2. Use layout-aware document analysis that preserves rows, selection marks and text spans
  3. Use field confidence and source review for ambiguous numeric values
  4. Classify document type before routing to the relevant extraction analyzer

Explanation

Correct Answer

D:

Different document kinds have distinct field schemas and review paths. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Some modalities and features depend on resource and API version. That is not sufficient here: Different document kinds have distinct field schemas and review paths.

B:

Ordinary plain-text OCR may lose table relationships and checkbox states. That is not sufficient here: Different document kinds have distinct field schemas and review paths.

C:

A low-confidence amount must not be silently treated as definitive. That is not sufficient here: Different document kinds have distinct field schemas and review paths.

Question 325

An engineering review documents this requirement: A production workflow requires stable Content Understanding capabilities rather than preview experiments. Select the most appropriate solution.

  1. Preserve table row-column structure and validate numeric totals
  2. Use field confidence and source review for ambiguous numeric values
  3. Prefer the GA API version and features unless preview use is explicitly approved
  4. Check feature, model and regional availability before creating an analyzer

Explanation

Correct Answer

C:

Preview-only features may have different availability and contracts. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Cell relationships are necessary to check item totals. That is not sufficient here: Preview-only features may have different availability and contracts.

B:

A low-confidence amount must not be silently treated as definitive. That is not sufficient here: Preview-only features may have different availability and contracts.

D:

Some modalities and features depend on resource and API version. That is not sufficient here: Preview-only features may have different availability and contracts.

Question 326

The approved design action is: Version procedures and limit grounding to the latest authorized operational guidance. Which test result would BEST establish that it worked?

  1. A simulated timeout yields a failure status without a fabricated numeric balance
  2. A legally ambiguous case offers appropriate caveats and referral
  3. Missing dosage context triggers abstention and a review route
  4. A changed safety instruction is used after the approved document refresh

Explanation

Correct Answer

D:

A precise explanation of an obsolete procedure can still be dangerous. The expected acceptance evidence is: A changed safety instruction is used after the approved document refresh. This observation directly tests the stated behavior.

Incorrect Answers

A:

A fluent generation cannot substitute for missing authoritative transaction data. This observation does not establish the required result: A changed safety instruction is used after the approved document refresh.

B:

Transparency reduces mistaken reliance on unsupported professional guarantees. This observation does not establish the required result: A changed safety instruction is used after the approved document refresh.

C:

Safety-critical recommendations require verified constraints outside open-ended generation. This observation does not establish the required result: A changed safety instruction is used after the approved document refresh.

Question 327

The approved design action is: Evaluate custom phrase hints or supported speech customization on representative terms. Which test result would BEST establish that it worked?

  1. Labeled specialty phrases are transcribed with reduced errors
  2. The output audio reads the approved sentence intelligibly
  3. The generated audio plays through the selected output device
  4. The transcript matches a labeled spoken test phrase

Explanation

Correct Answer

A:

Domain-specific words may require biasing or adaptation beyond a generic recognizer. The expected acceptance evidence is: Labeled specialty phrases are transcribed with reduced errors. This observation directly tests the stated behavior.

Incorrect Answers

B:

Speech synthesis generates audio waveforms from supplied text. This observation does not establish the required result: Labeled specialty phrases are transcribed with reduced errors.

C:

Successful synthesis does not guarantee local audio is routed to a speaker. This observation does not establish the required result: Labeled specialty phrases are transcribed with reduced errors.

D:

Speech recognition converts waveform features to text tokens. This observation does not establish the required result: Labeled specialty phrases are transcribed with reduced errors.

Question 328

An engineering review documents this requirement: A support chatbot is required to respond in a fixed structured format. Select the most appropriate solution.

  1. Include a concise output schema with valid and invalid examples where appropriate
  2. Write an instruction to identify missing inputs and request clarification before tools
  3. Handle tool timeout as a typed error and preserve partial workflow state
  4. State the role, goal, provided context, output requirement and constraints clearly

Explanation

Correct Answer

A:

Explicit examples can improve adherence to bounded output conventions. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

B:

Prompts can define required preconditions but tools must still enforce them. That is not sufficient here: Explicit examples can improve adherence to bounded output conventions.

C:

Timeout handling should not be reported as a successful action. That is not sufficient here: Explicit examples can improve adherence to bounded output conventions.

D:

Specific instructions reduce ambiguity about what constitutes success. That is not sufficient here: Explicit examples can improve adherence to bounded output conventions.

Question 329

The approved design action is: Specify factual boundaries and check generated claims against approved evidence. Which test result would BEST establish that it worked?

  1. The summary references statements supported by the supplied passage
  2. A generated claim resolves to an authorized supporting source
  3. A valid identity with required resource role succeeds in the test
  4. An injected page fails to invoke an unauthorized tool

Explanation

Correct Answer

B:

Prompt instructions must be paired with evidence verification for consequential facts. The expected acceptance evidence is: A generated claim resolves to an authorized supporting source. This observation directly tests the stated behavior.

Incorrect Answers

A:

Grounding constrains the answer to the available text and provenance. This observation does not establish the required result: A generated claim resolves to an authorized supporting source.

C:

Authentication proves caller identity and authorization grants resource access. This observation does not establish the required result: A generated claim resolves to an authorized supporting source.

D:

External content cannot replace privileged system behavior. This observation does not establish the required result: A generated claim resolves to an authorized supporting source.

Question 330

Troubleshooting report: The app assumes one image caption contains all structured outputs. Which correction is MOST directly targeted to this failure?

  1. Request the needed visual features explicitly
  2. Route to the text-to-image mode with intended inputs only
  3. Add confidence gating and supporting evidence
  4. Use aspect-ratio-preserving crop or padding

Explanation

Correct Answer

A:

This correction directly addresses the reported failure. Different visual outputs describe text, scene classes and detected people. The targeted change is: Request the needed visual features explicitly.

Incorrect Answers

B:

Generation from text is distinct from image editing. In the stated case, troubleshooting report: The app assumes one image caption contains all structured outputs; “Route to the text-to-image mode with intended inputs only” does not target that failure.

C:

Generated visual interpretations can be wrong even when phrased fluently. In the stated case, troubleshooting report: The app assumes one image caption contains all structured outputs; “Add confidence gating and supporting evidence” does not target that failure.

D:

Smart cropping differs from simply stretching pixels. In the stated case, troubleshooting report: The app assumes one image caption contains all structured outputs; “Use aspect-ratio-preserving crop or padding” does not target that failure.

Microsoft Azure AI Fundamentals (AI-901) Practice Tests