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 75

Question 740

Troubleshooting report: The assistant returns free-form prose that breaks an app parser. Which correction is MOST directly targeted to this failure?

  1. Require a completed tool result and error-path response
  2. Use the supported image-content input and multimodal deployment
  3. Tighten the output contract and apply post-response validation
  4. Keep policy instructions separate from lower-trust data

Explanation

Correct Answer

C:

This correction directly addresses the reported failure. Explicit examples can improve adherence to bounded output conventions. The targeted change is: Tighten the output contract and apply post-response validation.

Incorrect Answers

A:

Timeout handling should not be reported as a successful action. In the stated case, troubleshooting report: The assistant returns free-form prose that breaks an app parser; “Require a completed tool result and error-path response” does not target that failure.

B:

The model must receive the actual visual content to reason about it. In the stated case, troubleshooting report: The assistant returns free-form prose that breaks an app parser; “Use the supported image-content input and multimodal deployment” does not target that failure.

D:

High-priority instructions should describe approved behavior and escalation rules. In the stated case, troubleshooting report: The assistant returns free-form prose that breaks an app parser; “Keep policy instructions separate from lower-trust data” does not target that failure.

Question 741

A solution team has selected this control: Specify the output contract and validate returned fields against the schema. Which observation is the most direct acceptance evidence?

  1. The response contains only permitted fields with correct types
  2. The answer mentions relevant visual details unique to the uploaded image
  3. Repeated events yield at most one order creation under the same operation ID
  4. A representative maximum-size test stays within documented budgets

Explanation

Correct Answer

A:

Model output constraints help downstream parsing but still require validation. The expected acceptance evidence is: The response contains only permitted fields with correct types. This observation directly tests the stated behavior.

Incorrect Answers

B:

The model must receive the actual visual content to reason about it. This observation does not establish the required result: The response contains only permitted fields with correct types.

C:

A timeout does not prove that the original mutation failed. This observation does not establish the required result: The response contains only permitted fields with correct types.

D:

Capabilities and limits vary by model deployment. This observation does not establish the required result: The response contains only permitted fields with correct types.

Question 742

An Azure-based AI team must satisfy this objective: An AI résumé screener performs differently on documents formatted for assistive technology. Which design choice is best?

  1. Disclose collection purpose and retention period before capturing sensitive audio
  2. Maintain a governed feature inventory and trace decisions to policy
  3. Test representative document layouts and accessibility-oriented inputs
  4. Measure false positives on approved accessibility scenarios and refine thresholds

Explanation

Correct Answer

C:

Inclusion requires robust input handling beyond a single document template. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Privacy requires meaningful notice and bounded handling of personal data. That is not sufficient here: Inclusion requires robust input handling beyond a single document template.

B:

Accountability requires interpretable reasons for consequential decisions. That is not sufficient here: Inclusion requires robust input handling beyond a single document template.

D:

Safety controls should not overblock permitted assistance. That is not sufficient here: Inclusion requires robust input handling beyond a single document template.

Question 743

Troubleshooting report: Every sentence is attributed to the first speaker. Which correction is MOST directly targeted to this failure?

  1. Preserve segment timestamps and review rapid events separately when sampling might miss them
  2. Mark the field unreadable and request manual correction
  3. Keep transcript anchors and validate extracted tasks
  4. Enable appropriate diarization and handle ambiguous overlap

Explanation

Correct Answer

D:

This correction directly addresses the reported failure. Conversation extraction needs more than a single flattened text stream. The targeted change is: Enable appropriate diarization and handle ambiguous overlap.

Incorrect Answers

A:

Temporal evidence supports the timing of observed events, but approximately one frame per second cannot guarantee subsecond event capture. In the stated case, troubleshooting report: Every sentence is attributed to the first speaker; “Preserve segment timestamps and review rapid events separately when sampling might miss them” does not target that failure.

B:

Low-quality inputs can make extraction genuinely uncertain. In the stated case, troubleshooting report: Every sentence is attributed to the first speaker; “Mark the field unreadable and request manual correction” does not target that failure.

C:

Transcription and summarization are separate results with different validation. In the stated case, troubleshooting report: Every sentence is attributed to the first speaker; “Keep transcript anchors and validate extracted tasks” does not target that failure.

Question 744

The approved design action is: Use typed state fields and validate identifiers at each tool boundary. Which test result would BEST establish that it worked?

  1. The answer mentions relevant visual details unique to the uploaded image
  2. The chosen model meets labeled performance targets at lower cost
  3. The difference can be tied to an explicit configuration mismatch
  4. The same authorized case ID is observed in every step receipt

Explanation

Correct Answer

D:

Structured state prevents subtle substitution of unrelated customer records. The expected acceptance evidence is: The same authorized case ID is observed in every step receipt. This observation directly tests the stated behavior.

Incorrect Answers

A:

The model must receive the actual visual content to reason about it. This observation does not establish the required result: The same authorized case ID is observed in every step receipt.

B:

Lower-cost deployment is acceptable only if accuracy and safety floors remain met. This observation does not establish the required result: The same authorized case ID is observed in every step receipt.

C:

Environment drift can change behavior without code edits. This observation does not establish the required result: The same authorized case ID is observed in every step receipt.

Question 745

Troubleshooting report: The system returns one image-wide classification label. Which correction is MOST directly targeted to this failure?

  1. Request tags and parse the tag collection
  2. Use detection instead of whole-image classification
  3. Request a clearer image or report uncertainty
  4. Use image captioning with verified visual input

Explanation

Correct Answer

B:

This correction directly addresses the reported failure. Object detection reports which objects appear and where they occur. The targeted change is: Use detection instead of whole-image classification.

Incorrect Answers

A:

Tags summarize recognized concepts as labels. In the stated case, troubleshooting report: The system returns one image-wide classification label; “Request tags and parse the tag collection” does not target that failure.

C:

Visual reasoning is not proof of an exact value when axes are unclear. In the stated case, troubleshooting report: The system returns one image-wide classification label; “Request a clearer image or report uncertainty” does not target that failure.

D:

Captioning produces a sentence-level description rather than a coordinate list. In the stated case, troubleshooting report: The system returns one image-wide classification label; “Use image captioning with verified visual input” does not target that failure.

Question 746

An acceptance tester needs to validate: Require a missing-field status rather than generated plausible content. Which observed result proves the intended behavior?

  1. Quoted text matches the time-aligned source transcript
  2. A question links to the correct contract section and page
  3. The output identifies both amount and confirmed currency
  4. The missing field is returned as null or flagged unknown

Explanation

Correct Answer

D:

Extraction should preserve absence and distinguish it from zero. The expected acceptance evidence is: The missing field is returned as null or flagged unknown. This observation directly tests the stated behavior.

Incorrect Answers

A:

Generated summaries are paraphrases and not guaranteed verbatim quotes. This observation does not establish the required result: The missing field is returned as null or flagged unknown.

B:

Structured layout and provenance let users verify a quoted clause. This observation does not establish the required result: The missing field is returned as null or flagged unknown.

C:

A currency symbol or amount alone may not establish financial meaning. This observation does not establish the required result: The missing field is returned as null or flagged unknown.

Question 747

An Azure AI solution uses the following approved control: Review precision, recall and the confusion matrix rather than accuracy alone. What observable result should pass QA?

  1. Repeated structured cases follow the expected schema more consistently
  2. The holdout report identifies missed positives and false alarms explicitly
  3. The model/deployment capability check and a spoken-audio test confirm that this endpoint supports transcription
  4. The same brief yields a wider range of acceptable styles without broken constraints

Explanation

Correct Answer

B:

High accuracy can conceal failure to detect rare positive events. The expected acceptance evidence is: The holdout report identifies missed positives and false alarms explicitly. This observation directly tests the stated behavior.

Incorrect Answers

A:

Lower randomness often improves consistency but does not guarantee correctness. This observation does not establish the required result: The holdout report identifies missed positives and false alarms explicitly.

C:

Model capabilities must include the required audio modality before the client can obtain speech-to-text results. This observation does not establish the required result: The holdout report identifies missed positives and false alarms explicitly.

D:

More varied token sampling can increase creative alternatives. This observation does not establish the required result: The holdout report identifies missed positives and false alarms explicitly.

Question 748

An engineering review documents this requirement: A bank receives scanned application forms and needs account fields in a database. Select the most appropriate solution.

  1. Combine speech recognition, language translation, and appropriate speech synthesis
  2. Combine video frame analysis with temporal segmentation
  3. Use document information extraction with a typed field schema
  4. Use a visual classification or detection model appropriate to whether location matters

Explanation

Correct Answer

C:

Document extraction maps unstructured layouts into structured values. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Speech translation spans audio input, semantic transfer and optional output audio. That is not sufficient here: Document extraction maps unstructured layouts into structured values.

B:

Video understanding retains order and time, unlike single-image tagging. That is not sufficient here: Document extraction maps unstructured layouts into structured values.

D:

The task chooses a label, with localization needed only when multiple signs appear. That is not sufficient here: Document extraction maps unstructured layouts into structured values.

Question 749

A solution team has selected this control: Place durable application behavior constraints in supported high-priority instructions. Which observation is the most direct acceptance evidence?

  1. The smaller candidate meets the acceptance floor with lower cost where appropriate
  2. Repeated structured cases follow the expected schema more consistently
  3. Reintroducing relevant context changes the answer in a controlled test
  4. A user request cannot override the controlling system-level instructions in tests

Explanation

Correct Answer

D:

Instruction roles help distinguish application policy from user task text. The expected acceptance evidence is: A user request cannot override the controlling system-level instructions in tests. This observation directly tests the stated behavior.

Incorrect Answers

A:

Model size alone does not establish suitability for a particular task. This observation does not establish the required result: A user request cannot override the controlling system-level instructions in tests.

B:

Lower randomness often improves consistency but does not guarantee correctness. This observation does not establish the required result: A user request cannot override the controlling system-level instructions in tests.

C:

A model conditions its output on supplied instructions and conversation text. This observation does not establish the required result: A user request cannot override the controlling system-level instructions in tests.

Question 750

An Azure AI Fundamentals solution has this requirement: A developer wants to compare prompt revisions objectively. Which implementation most directly addresses it?

  1. Limit retrieval and chat context to the authenticated case scope
  2. Use a versioned evaluation set with stable scoring and test inputs
  3. Write an instruction to identify missing inputs and request clarification before tools
  4. Send the image in a supported multimodal message along with the question

Explanation

Correct Answer

B:

Anecdotal success on different prompts cannot establish an improvement. This implementation addresses the precise goal rather than an adjacent AI task.

Incorrect Answers

A:

Source scoping enforces privacy and also improves answer relevance. That is not sufficient here: Anecdotal success on different prompts cannot establish an improvement.

C:

Prompts can define required preconditions but tools must still enforce them. That is not sufficient here: Anecdotal success on different prompts cannot establish an improvement.

D:

The model must receive the actual visual content to reason about it. That is not sufficient here: Anecdotal success on different prompts cannot establish an improvement.

Microsoft Azure AI Fundamentals (AI-901) Practice Tests