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 10

Question 90

An Azure-based AI team must satisfy this objective: A virtual assistant is deployed to staff without informing them it is AI. Which design choice is best?

  1. Test accuracy on representative lighting and camera conditions and provide a safe fallback
  2. Redact personal fields before telemetry storage and control log access
  3. Disclose the automated nature and supported escalation route in the interface
  4. Treat retrieved content as untrusted evidence and prevent it from changing tool authority

Explanation

Correct Answer

C:

Transparency helps users assess the scope and limitations of the assistance. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Reliability demands testing the actual operating environment, not just clean samples. That is not sufficient here: Transparency helps users assess the scope and limitations of the assistance.

B:

Troubleshooting does not justify reproducing sensitive application records. That is not sufficient here: Transparency helps users assess the scope and limitations of the assistance.

D:

Lower-trust text is not a privileged command channel. That is not sufficient here: Transparency helps users assess the scope and limitations of the assistance.

Question 91

Troubleshooting report: The test set has no metadata about device types. Which correction is MOST directly targeted to this failure?

  1. Document feature lineage and remove unapproved decision features
  2. Execute and audit the supported deletion workflow
  3. Archive the actual decision and versioned provenance with privacy minimization
  4. Label and evaluate representative scans by acquisition equipment

Explanation

Correct Answer

D:

This correction directly addresses the reported failure. Reliability requires detecting distribution shifts hidden in aggregate accuracy. The targeted change is: Label and evaluate representative scans by acquisition equipment.

Incorrect Answers

A:

Accountability requires interpretable reasons for consequential decisions. In the stated case, troubleshooting report: The test set has no metadata about device types; “Document feature lineage and remove unapproved decision features” does not target that failure.

B:

Accountability requires evidence of actual data lifecycle actions. In the stated case, troubleshooting report: The test set has no metadata about device types; “Execute and audit the supported deletion workflow” does not target that failure.

C:

Auditability requires the original decision evidence and version identifiers; regenerating model text is not guaranteed to be identical. In the stated case, troubleshooting report: The test set has no metadata about device types; “Archive the actual decision and versioned provenance with privacy minimization” does not target that failure.

Question 92

An Azure AI Fundamentals solution has this requirement: A spoken-command bot needs punctuation in the final transcript. Which implementation most directly addresses it?

  1. Match the speech resource region or endpoint to the SDK configuration
  2. Enable or use supported punctuation formatting with appropriate post-processing
  3. Evaluate custom phrase hints or supported speech customization on representative terms
  4. Use supported voice and SSML prosody rate controls

Explanation

Correct Answer

B:

Speech text may require punctuation inference distinct from word recognition. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Region or endpoint mismatch prevents requests reaching the correct resource. That is not sufficient here: Speech text may require punctuation inference distinct from word recognition.

C:

Domain-specific words may require biasing or adaptation beyond a generic recognizer. That is not sufficient here: Speech text may require punctuation inference distinct from word recognition.

D:

Voice selection and prosody can influence delivery without changing the text. That is not sufficient here: Speech text may require punctuation inference distinct from word recognition.

Question 93

A solution team has selected this control: Use timestamped evidence-linked video segments and explicitly account for frame-sampling limits. Which observation is the most direct acceptance evidence?

  1. The decoded barcode matches the printed test label
  2. Total mismatches trigger a review rather than automatic posting
  3. Observed labeled events receive evidence-backed intervals and brief unobserved events are flagged for review
  4. The resulting record maps each value to its correct page

Explanation

Correct Answer

C:

Temporal evidence supports the timing of observed events, but approximately one frame per second cannot guarantee subsecond event capture. The expected acceptance evidence is: Observed labeled events receive evidence-backed intervals and brief unobserved events are flagged for review. This observation directly tests the stated behavior.

Incorrect Answers

A:

A barcode is a structured visual symbol not ordinary OCR text. This observation does not establish the required result: Observed labeled events receive evidence-backed intervals and brief unobserved events are flagged for review.

B:

Independent business rules catch plausible extraction errors. This observation does not establish the required result: Observed labeled events receive evidence-backed intervals and brief unobserved events are flagged for review.

D:

Page order and references are part of document provenance. This observation does not establish the required result: Observed labeled events receive evidence-backed intervals and brief unobserved events are flagged for review.

Question 94

A solution team has selected this control: Use an agent with scoped retrieval and separately authorized mutation tools. Which observation is the most direct acceptance evidence?

  1. A logged tool receipt proves a permitted ticket was created
  2. Workers without matched helmet detections are flagged for review
  3. Read requests succeed while unauthorized writes are blocked
  4. Suggested products are relevant and meet inventory/authorization rules

Explanation

Correct Answer

C:

Agentic workflows combine information access with controlled actions. The expected acceptance evidence is: Read requests succeed while unauthorized writes are blocked. This observation directly tests the stated behavior.

Incorrect Answers

A:

Agentic workloads combine reasoning and bounded external actions. This observation does not establish the required result: Read requests succeed while unauthorized writes are blocked.

B:

Detection relates objects to positions for compliance checks. This observation does not establish the required result: Read requests succeed while unauthorized writes are blocked.

D:

Semantic vectors capture related concepts while filters enforce eligibility. This observation does not establish the required result: Read requests succeed while unauthorized writes are blocked.

Question 95

Troubleshooting report: A plain OCR text stream loses column associations. Which correction is MOST directly targeted to this failure?

  1. Define extraction fields and validate values
  2. Use layout-aware structured invoice extraction
  3. Train or configure intent classification with a bounded label set
  4. Use a near-real-time speech translation pipeline

Explanation

Correct Answer

B:

This correction directly addresses the reported failure. Table extraction associates quantities, descriptions and prices by row. The targeted change is: Use layout-aware structured invoice extraction.

Incorrect Answers

A:

Document extraction maps unstructured layouts into structured values. In the stated case, troubleshooting report: A plain OCR text stream loses column associations; “Define extraction fields and validate values” does not target that failure.

C:

Classification maps text to one of several predefined categories. In the stated case, troubleshooting report: A plain OCR text stream loses column associations; “Train or configure intent classification with a bounded label set” does not target that failure.

D:

Speech translation spans audio input, semantic transfer and optional output audio. In the stated case, troubleshooting report: A plain OCR text stream loses column associations; “Use a near-real-time speech translation pipeline” does not target that failure.

Question 96

An AI operations team is testing two distinct capabilities. Failure (1): Only English test prompts were approved before multilingual launch. Failure (2): Audio recordings persist indefinitely in an unrestricted bucket. Which TWO specific corrections should the team apply?

  1. Add adversarial and exception-focused cases before promotion
  2. Exclude obsolete material with approval and timestamp filters
  3. Run native-language acceptance cases with verified translations and experts
  4. Add auditable explanation records and an appeals workflow
  5. Apply data minimization, retention and permission controls

Explanation

Correct Answers

C:

Correct for failure (1). Inclusion requires equivalent safety and meaning across supported locales. The proposed correction directly addresses that reported defect.

E:

Correct for failure (2). Privacy requires meaningful notice and bounded handling of personal data. It independently corrects the second defect.

Incorrect Answers

A:

A high overall score can conceal severe failure on unusual inputs. In this case the first outcome requires the team to evaluate instructions and fallback quality in each supported language, and the second requires it to disclose collection purpose and retention period before capturing sensitive audio. This option does not replace those two separate controls.

B:

A precise explanation of an obsolete procedure can still be dangerous. In this case the first outcome requires the team to evaluate instructions and fallback quality in each supported language, and the second requires it to disclose collection purpose and retention period before capturing sensitive audio. This option does not replace those two separate controls.

D:

Accountability includes traceable responsibility and appropriate contestability. In this case the first outcome requires the team to evaluate instructions and fallback quality in each supported language, and the second requires it to disclose collection purpose and retention period before capturing sensitive audio. This option does not replace those two separate controls.

Question 97

The approved design action is: Run versioned safety regressions and block promotion on failed high-severity cases. Which test result would BEST establish that it worked?

  1. The unchanged safety suite detects the new failure before deployment
  2. A legally ambiguous case offers appropriate caveats and referral
  3. Labeled accessible-use examples pass while harmful variants remain blocked
  4. The returned metric reconciles to the approved source table

Explanation

Correct Answer

A:

Reliability includes preventing behavior regression across model versions. The expected acceptance evidence is: The unchanged safety suite detects the new failure before deployment. This observation directly tests the stated behavior.

Incorrect Answers

B:

Transparency reduces mistaken reliance on unsupported professional guarantees. This observation does not establish the required result: The unchanged safety suite detects the new failure before deployment.

C:

Safety controls should not overblock permitted assistance. This observation does not establish the required result: The unchanged safety suite detects the new failure before deployment.

D:

A numeric-looking answer is not proof that a measure was computed. This observation does not establish the required result: The unchanged safety suite detects the new failure before deployment.

Question 98

An engineering review documents this requirement: A utilities firm needs an estimate of electricity use next week. Select the most appropriate solution.

  1. Use regression or forecasting appropriate to time-series data
  2. Use speech-to-text transcription before indexing call content
  3. Use PII-aware entity recognition with appropriate redaction
  4. Use image classification for the requested category

Explanation

Correct Answer

A:

Forecasts predict future numeric quantities rather than discrete tags. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

B:

Speech recognition converts speech into words suitable for search. That is not sufficient here: Forecasts predict future numeric quantities rather than discrete tags.

C:

Entity extraction locates sensitive spans for privacy handling. That is not sufficient here: Forecasts predict future numeric quantities rather than discrete tags.

D:

Image classification predicts image-level labels. That is not sufficient here: Forecasts predict future numeric quantities rather than discrete tags.

Question 99

A project needs the following AI behavior: A deployment must distinguish object tags from OCR text in a result. What should the designer implement?

  1. Generate and edit concise factual alt text describing significant content
  2. Use the box coordinates to locate detected people in the source image
  3. Use text-to-image generation and keep the input photo out of the edit request
  4. Keep recognized visual labels separate from text-read lines and words

Explanation

Correct Answer

D:

Tags describe concepts while OCR reports character content. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Accessible captions should communicate image purpose without invented details. That is not sufficient here: Tags describe concepts while OCR reports character content.

B:

Localization metadata is tied to pixel regions, not just labels. That is not sufficient here: Tags describe concepts while OCR reports character content.

C:

Generation from text is distinct from image editing. That is not sufficient here: Tags describe concepts while OCR reports character content.

Question 100

An acceptance tester needs to validate: Enable supported document-field confidence and grounding, then calibrate field-specific review thresholds using labeled samples. Which observed result proves the intended behavior?

  1. Mixed-language fields are transcribed correctly on labeled samples
  2. A reviewer confirms the selected clauses and visible signature region from the source, without claiming a verified legal signature
  3. Validated fields above tested thresholds proceed while uncertain or inconsistent fields enter review
  4. Extracted rows align with the original form cells

Explanation

Correct Answer

C:

Content Understanding confidence applies to supported document analyzers; confidence estimates alone do not prove field correctness. The expected acceptance evidence is: Validated fields above tested thresholds proceed while uncertain or inconsistent fields enter review. This observation directly tests the stated behavior.

Incorrect Answers

A:

Recognition accuracy depends on script and language support. This observation does not establish the required result: Validated fields above tested thresholds proceed while uncertain or inconsistent fields enter review.

B:

Selection-mark extraction is available with GA document analysis, but dedicated signature-location detection is available only in the 2026-06-01-preview API and cannot establish legal validity. This observation does not establish the required result: Validated fields above tested thresholds proceed while uncertain or inconsistent fields enter review.

D:

Ordinary plain-text OCR may lose table relationships and checkbox states. This observation does not establish the required result: Validated fields above tested thresholds proceed while uncertain or inconsistent fields enter review.

Microsoft Azure AI Fundamentals (AI-901) Practice Tests