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 45

Question 440

Troubleshooting report: OCR reads numbers without their row associations. Which correction is MOST directly targeted to this failure?

  1. Use table-aware layout extraction and numeric validation
  2. Configure supported language handling and test each script
  3. Use barcode decoding and validate content
  4. Preserve actual section/page references through retrieval

Explanation

Correct Answer

A:

This correction directly addresses the reported failure. Cell relationships are necessary to check item totals. The targeted change is: Use table-aware layout extraction and numeric validation.

Incorrect Answers

B:

Recognition accuracy depends on script and language support. In the stated case, troubleshooting report: OCR reads numbers without their row associations; “Configure supported language handling and test each script” does not target that failure.

C:

A barcode is a structured visual symbol not ordinary OCR text. In the stated case, troubleshooting report: OCR reads numbers without their row associations; “Use barcode decoding and validate content” does not target that failure.

D:

Structured layout and provenance let users verify a quoted clause. In the stated case, troubleshooting report: OCR reads numbers without their row associations; “Preserve actual section/page references through retrieval” does not target that failure.

Question 441

An Azure-based AI team must satisfy this objective: A customer support model uses legal advice wording that sounds absolute. Which design choice is best?

  1. Separate informational assistance from qualified professional decisions and express uncertainty
  2. Use validated data retrieval and source-backed numerical responses
  3. Redact personal fields before telemetry storage and control log access
  4. Set explicit uncertainty thresholds and route high-risk decisions to qualified review

Explanation

Correct Answer

A:

Transparency reduces mistaken reliance on unsupported professional guarantees. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

B:

A numeric-looking answer is not proof that a measure was computed. That is not sufficient here: Transparency reduces mistaken reliance on unsupported professional guarantees.

C:

Troubleshooting does not justify reproducing sensitive application records. That is not sufficient here: Transparency reduces mistaken reliance on unsupported professional guarantees.

D:

Safety-critical recommendations require verified constraints outside open-ended generation. That is not sufficient here: Transparency reduces mistaken reliance on unsupported professional guarantees.

Question 442

The approved design action is: Use a supervised classification model with representative labeled cases. Which test result would BEST establish that it worked?

  1. Predicted kWh values are scored against observed readings
  2. Held-out defect images meet the tested localization and per-class detection thresholds
  3. Unseen examples have measured results independent of training
  4. Holdout examples are assigned valid classes with measured accuracy

Explanation

Correct Answer

D:

Classification predicts discrete labels rather than a continuous numeric target. The expected acceptance evidence is: Holdout examples are assigned valid classes with measured accuracy. This observation directly tests the stated behavior.

Incorrect Answers

A:

Regression predicts continuous quantities under a defined error metric. This observation does not establish the required result: Holdout examples are assigned valid classes with measured accuracy.

B:

An appropriate spatial detection model must localize the defect classes, not merely assign an overall picture label. This observation does not establish the required result: Holdout examples are assigned valid classes with measured accuracy.

C:

A model can memorize training examples without generalizing. This observation does not establish the required result: Holdout examples are assigned valid classes with measured accuracy.

Question 443

Troubleshooting report: Generated copy attributes fabricated words to an identifiable customer. Which correction is MOST directly targeted to this failure?

  1. Remove the false attribution and require documentary consent
  2. Add low-light and motion-blur scenarios to the evaluation set
  3. Reconcile the provider transaction ID and actual status before confirmation
  4. Replace impersonating presentation with explicit synthetic-agent notice

Explanation

Correct Answer

A:

This correction directly addresses the reported failure. Transparency prohibits presenting invented testimony as genuine. The targeted change is: Remove the false attribution and require documentary consent.

Incorrect Answers

B:

Reliability demands testing the actual operating environment, not just clean samples. In the stated case, troubleshooting report: Generated copy attributes fabricated words to an identifiable customer; “Add low-light and motion-blur scenarios to the evaluation set” does not target that failure.

C:

Generated text is not evidence of external side effects. In the stated case, troubleshooting report: Generated copy attributes fabricated words to an identifiable customer; “Reconcile the provider transaction ID and actual status before confirmation” does not target that failure.

D:

Transparency prevents users from falsely assuming they are speaking with a human. In the stated case, troubleshooting report: Generated copy attributes fabricated words to an identifiable customer; “Replace impersonating presentation with explicit synthetic-agent notice” does not target that failure.

Question 444

Troubleshooting report: The interface says stopped while background capture continues. Which correction is MOST directly targeted to this failure?

  1. Set the supported Spanish locale and verify accuracy
  2. Correct streaming buffer and session lifecycle
  3. Load the deployed speech resource's region and endpoint
  4. Close the capture stream and update permission controls

Explanation

Correct Answer

D:

This correction directly addresses the reported failure. User control of capture must be enforced at the device or application layer. The targeted change is: Close the capture stream and update permission controls.

Incorrect Answers

A:

Recognition models need the appropriate supported language settings. In the stated case, troubleshooting report: The interface says stopped while background capture continues; “Set the supported Spanish locale and verify accuracy” does not target that failure.

B:

Real-time audio pipelines need coordinated capture and recognition start. In the stated case, troubleshooting report: The interface says stopped while background capture continues; “Correct streaming buffer and session lifecycle” does not target that failure.

C:

Region or endpoint mismatch prevents requests reaching the correct resource. In the stated case, troubleshooting report: The interface says stopped while background capture continues; “Load the deployed speech resource's region and endpoint” does not target that failure.

Question 445

A project needs the following AI behavior: A document extractor returns a field that was absent from the input. What should the designer implement?

  1. Distinguish transcript passages from generated summaries and retain timestamps
  2. Require a missing-field status rather than generated plausible content
  3. Define a custom analyzer for consistent target field meanings across templates
  4. Preserve document IDs, versions and extracted field evidence with search results

Explanation

Correct Answer

B:

Extraction should preserve absence and distinguish it from zero. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Generated summaries are paraphrases and not guaranteed verbatim quotes. That is not sufficient here: Extraction should preserve absence and distinguish it from zero.

C:

A schema-driven analyzer identifies business fields independent of fixed coordinates. That is not sufficient here: Extraction should preserve absence and distinguish it from zero.

D:

Verifiable provenance differentiates a cited answer from guesswork. That is not sufficient here: Extraction should preserve absence and distinguish it from zero.

Question 446

Troubleshooting report: Every utterance is processed under one fixed English locale. Which correction is MOST directly targeted to this failure?

  1. Configure playback routing and compatible output decoding
  2. Invoke a text-to-speech voice and compatible audio format
  3. Set the supported Spanish locale and verify accuracy
  4. Enable supported language detection with constrained candidates

Explanation

Correct Answer

D:

This correction directly addresses the reported failure. Automatic language detection chooses among an approved set of languages. The targeted change is: Enable supported language detection with constrained candidates.

Incorrect Answers

A:

Successful synthesis does not guarantee local audio is routed to a speaker. In the stated case, troubleshooting report: Every utterance is processed under one fixed English locale; “Configure playback routing and compatible output decoding” does not target that failure.

B:

Speech synthesis generates audio waveforms from supplied text. In the stated case, troubleshooting report: Every utterance is processed under one fixed English locale; “Invoke a text-to-speech voice and compatible audio format” does not target that failure.

C:

Recognition models need the appropriate supported language settings. In the stated case, troubleshooting report: Every utterance is processed under one fixed English locale; “Set the supported Spanish locale and verify accuracy” does not target that failure.

Question 447

Troubleshooting report: The app returns only a global image caption. Which correction is MOST directly targeted to this failure?

  1. Detect people and helmets and evaluate spatial associations
  2. Add bounded conversation state and retrieved evidence
  3. Define extraction fields and validate values
  4. Treat absent fields as unknown and request a better image

Explanation

Correct Answer

A:

This correction directly addresses the reported failure. Detection relates objects to positions for compliance checks. The targeted change is: Detect people and helmets and evaluate spatial associations.

Incorrect Answers

B:

The assistant should incorporate context while remaining connected to reliable sources. In the stated case, troubleshooting report: The app returns only a global image caption; “Add bounded conversation state and retrieved evidence” does not target that failure.

C:

Document extraction maps unstructured layouts into structured values. In the stated case, troubleshooting report: The app returns only a global image caption; “Define extraction fields and validate values” does not target that failure.

D:

Images of receipts need OCR/layout extraction before typed business values. In the stated case, troubleshooting report: The app returns only a global image caption; “Treat absent fields as unknown and request a better image” does not target that failure.

Question 448

Troubleshooting report: The system classifies only predefined malware families. Which correction is MOST directly targeted to this failure?

  1. Introduce a document classifier and route by type
  2. Apply anomaly scoring to normalized traffic features
  3. Detect people and helmets and evaluate spatial associations
  4. Use entity recognition and verify sensitive-entity recall

Explanation

Correct Answer

B:

This correction directly addresses the reported failure. Anomaly methods identify deviations rather than assigning preset incident labels. The targeted change is: Apply anomaly scoring to normalized traffic features.

Incorrect Answers

A:

Classification selects the extraction process matching the document category. In the stated case, troubleshooting report: The system classifies only predefined malware families; “Introduce a document classifier and route by type” does not target that failure.

C:

Detection relates objects to positions for compliance checks. In the stated case, troubleshooting report: The system classifies only predefined malware families; “Detect people and helmets and evaluate spatial associations” does not target that failure.

D:

Entity extraction locates sensitive spans for privacy handling. In the stated case, troubleshooting report: The system classifies only predefined malware families; “Use entity recognition and verify sensitive-entity recall” does not target that failure.

Question 449

Troubleshooting report: Only a system style rule is sent as a request. Which correction is MOST directly targeted to this failure?

  1. Use code validation and protected deployment controls
  2. Rewrite the prompt with explicit acceptance criteria
  3. Attach idempotency keys and verify tool receipts after reconnecting
  4. Add the actual user content to the chat message sequence

Explanation

Correct Answer

D:

This correction directly addresses the reported failure. The inference service needs task content to generate a relevant answer. The targeted change is: Add the actual user content to the chat message sequence.

Incorrect Answers

A:

Generated code must be validated, not treated as production-ready from fluency. In the stated case, troubleshooting report: Only a system style rule is sent as a request; “Use code validation and protected deployment controls” does not target that failure.

B:

Specific instructions reduce ambiguity about what constitutes success. In the stated case, troubleshooting report: Only a system style rule is sent as a request; “Rewrite the prompt with explicit acceptance criteria” does not target that failure.

C:

Client retries should distinguish read requests from side-effecting tool calls. In the stated case, troubleshooting report: Only a system style rule is sent as a request; “Attach idempotency keys and verify tool receipts after reconnecting” does not target that failure.

Question 450

An Azure AI Fundamentals solution has this requirement: An agent must answer only from company-approved product manuals. Which implementation most directly addresses it?

  1. Choose a model size using representative quality and cost benchmarks
  2. Set authorized knowledge sources and a no-source fallback
  3. Handle tool timeout as a typed error and preserve partial workflow state
  4. Externalize endpoint and deployment configuration per environment

Explanation

Correct Answer

B:

Retrieval access and abstention avoid inventing unsupported documentation. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Lower-cost deployment is acceptable only if accuracy and safety floors remain met. That is not sufficient here: Retrieval access and abstention avoid inventing unsupported documentation.

C:

Timeout handling should not be reported as a successful action. That is not sufficient here: Retrieval access and abstention avoid inventing unsupported documentation.

D:

A correct code path can still target the wrong resource after migration. That is not sufficient here: Retrieval access and abstention avoid inventing unsupported documentation.

Microsoft Azure AI Fundamentals (AI-901) Practice Tests